GingerLabsPlatform commited on
Commit
5b65000
·
verified ·
1 Parent(s): 731749d

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ models/fishaudioS2/s2-pro/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ models/fishaudioS2/s2-pro/overview.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ private: true
3
+ ---
4
+
5
+ # GingerLabs MiniMax H3 voice preprocessing runtime
6
+
7
+ Immutable RunPod cached-model bundle assembled from release-pinned sources. Do not modify this repository in place.
models/Qwen3-ASR-0.6B/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
models/Qwen3-ASR-0.6B/README.md ADDED
@@ -0,0 +1,1393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ pipeline_tag: automatic-speech-recognition
4
+ ---
5
+
6
+ # Qwen3-ASR
7
+
8
+ ## Overview
9
+
10
+ ### Introduction
11
+
12
+ <p align="center">
13
+ <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/qwen3_asr_introduction.png" width="90%"/>
14
+ <p>
15
+
16
+ The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. Experiments show that the 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs. Here are the main features:
17
+
18
+ * **All-in-one**: Qwen3-ASR-1.7B and Qwen3-ASR-0.6B support language identification and speech recognition for 30 languages and 22 Chinese dialects, so as to English accents from multiple countries and regions.
19
+
20
+ * **Excellent and Fast**: The Qwen3-ASR family ASR models maintains high-quality and robust recognition under complex acoustic environments and challenging text patterns. Qwen3-ASR-1.7B achieves strong performance on both open-sourced and internal benchmarks. While the 0.6B version achieves accuracy-efficient trade-off, it reaches 2000 times throughput at a concurrency of 128. They both achieve streaming / offline unified inference with single model and support transcribe long audio.
21
+
22
+ * **Novel and strong forced alignment Solution**: We introduce Qwen3-ForcedAligner-0.6B, which supports timestamp prediction for arbitrary units within up to 5 minutes of speech in 11 languages. Evaluations show its timestamp accuracy surpasses E2E based forced-alignment models.
23
+
24
+ * **Comprehensive inference toolkit**: In addition to open-sourcing the architectures and weights of the Qwen3-ASR series, we also release a powerful, full-featured inference framework that supports vLLM-based batch inference, asynchronous serving, streaming inference, timestamp prediction, and more.
25
+
26
+ ### Model Architecture
27
+
28
+ <p align="center">
29
+ <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/overview.jpg" width="100%"/>
30
+ <p>
31
+
32
+
33
+ ### Released Models Description and Download
34
+
35
+ Below is an introduction and download information for the Qwen3-ASR models. Please select and download the model that fits your needs.
36
+
37
+ | Model | Supported Languages | Supported Dialects | Inference Mode | Audio Types |
38
+ |---|---|---|---|---|
39
+ | Qwen3-ASR-1.7B & Qwen3-ASR-0.6B | Chinese (zh), English (en), Cantonese (yue), Arabic (ar), German (de), French (fr), Spanish (es), Portuguese (pt), Indonesian (id), Italian (it), Korean (ko), Russian (ru), Thai (th), Vietnamese (vi), Japanese (ja), Turkish (tr), Hindi (hi), Malay (ms), Dutch (nl), Swedish (sv), Danish (da), Finnish (fi), Polish (pl), Czech (cs), Filipino (fil), Persian (fa), Greek (el), Hungarian (hu), Macedonian (mk), Romanian (ro) | Anhui, Dongbei, Fujian, Gansu, Guizhou, Hebei, Henan, Hubei, Hunan, Jiangxi, Ningxia, Shandong, Shaanxi, Shanxi, Sichuan, Tianjin, Yunnan, Zhejiang, Cantonese (Hong Kong accent), Cantonese (Guangdong accent), Wu language, Minnan language. | Offline / Streaming | Speech, Singing Voice, Songs with BGM |
40
+ | Qwen3-ForcedAligner-0.6B | Chinese, English, Cantonese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish | -- | NAR | Speech |
41
+
42
+ During model loading in the `qwen-asr` package or vLLM, model weights will be downloaded automatically based on the model name. However, if your runtime environment does not allow downloading weights during execution, you can use the following commands to manually download the model weights to a local directory:
43
+
44
+ ```bash
45
+ # Download through ModelScope (recommended for users in Mainland China)
46
+ pip install -U modelscope
47
+ modelscope download --model Qwen/Qwen3-ASR-1.7B --local_dir ./Qwen3-ASR-1.7B
48
+ modelscope download --model Qwen/Qwen3-ASR-0.6B --local_dir ./Qwen3-ASR-0.6B
49
+ modelscope download --model Qwen/Qwen3-ForcedAligner-0.6B --local_dir ./Qwen3-ForcedAligner-0.6B
50
+ # Download through Hugging Face
51
+ pip install -U "huggingface_hub[cli]"
52
+ huggingface-cli download Qwen/Qwen3-ASR-1.7B --local-dir ./Qwen3-ASR-1.7B
53
+ huggingface-cli download Qwen/Qwen3-ASR-0.6B --local-dir ./Qwen3-ASR-0.6B
54
+ huggingface-cli download Qwen/Qwen3-ForcedAligner-0.6B --local-dir ./Qwen3-ForcedAligner-0.6B
55
+ ```
56
+
57
+
58
+ ## Quickstart
59
+
60
+ ### Environment Setup
61
+
62
+ The easiest way to use Qwen3-ASR is to install the `qwen-asr` Python package from PyPI. This will pull in the required runtime dependencies and allow you to load any released Qwen3-ASR model. If you’d like to simplify environment setup further, you can also use our official [Docker image](#docker). The `qwen-asr` package provides two backends: the transformers backend and the vLLM backend. For usage instructions for different backends, please refer to [Python Package Usage](#python-package-usage). We recommend using a **fresh, isolated environment** to avoid dependency conflicts with existing packages. You can create a clean Python 3.12 environment like this:
63
+
64
+ ```bash
65
+ conda create -n qwen3-asr python=3.12 -y
66
+ conda activate qwen3-asr
67
+ ```
68
+
69
+ Run the following command to get the minimal installation with transformers-backend support:
70
+
71
+ ```bash
72
+ pip install -U qwen-asr
73
+ ```
74
+
75
+ To enable the vLLM backend for faster inference and streaming support, run:
76
+
77
+ ```bash
78
+ pip install -U qwen-asr[vllm]
79
+ ```
80
+
81
+ If you want to develop or modify the code locally, install from source in editable mode:
82
+
83
+ ```bash
84
+ git clone https://github.com/QwenLM/Qwen3-ASR.git
85
+ cd Qwen3-ASR
86
+ pip install -e .
87
+ # support vLLM backend
88
+ # pip install -e ".[vllm]"
89
+ ```
90
+
91
+ Additionally, we recommend using FlashAttention 2 to reduce GPU memory usage and accelerate inference speed, especially for long inputs and large batch sizes.
92
+
93
+ ```bash
94
+ pip install -U flash-attn --no-build-isolation
95
+ ```
96
+
97
+ If your machine has less than 96GB of RAM and lots of CPU cores, run:
98
+
99
+ ```bash
100
+ MAX_JOBS=4 pip install -U flash-attn --no-build-isolation
101
+ ```
102
+
103
+ Also, you should have hardware that is compatible with FlashAttention 2. Read more about it in the official documentation of the [FlashAttention repository](https://github.com/Dao-AILab/flash-attention). FlashAttention 2 can only be used when a model is loaded in `torch.float16` or `torch.bfloat16`.
104
+
105
+ ### Python Package Usage
106
+
107
+ #### Quick Inference
108
+
109
+ The `qwen-asr` package provides two backends: **transformers backend** and **vLLM backend**. You can pass audio inputs as a local path, a URL, base64 data, or a `(np.ndarray, sr)` tuple, and run batch inference. To quickly try Qwen3-ASR, you can use `Qwen3ASRModel.from_pretrained(...)` for the transformers backend with the following code:
110
+
111
+ ```python
112
+ import torch
113
+ from qwen_asr import Qwen3ASRModel
114
+
115
+ model = Qwen3ASRModel.from_pretrained(
116
+ "Qwen/Qwen3-ASR-1.7B",
117
+ dtype=torch.bfloat16,
118
+ device_map="cuda:0",
119
+ # attn_implementation="flash_attention_2",
120
+ max_inference_batch_size=32, # Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
121
+ max_new_tokens=256, # Maximum number of tokens to generate. Set a larger value for long audio input.
122
+ )
123
+
124
+ results = model.transcribe(
125
+ audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
126
+ language=None, # set "English" to force the language
127
+ )
128
+
129
+ print(results[0].language)
130
+ print(results[0].text)
131
+ ```
132
+
133
+ If you want to return timestamps, pass `forced_aligner` and its init kwargs. Here is an example of batch inference with timestamps output:
134
+
135
+ ```python
136
+ import torch
137
+ from qwen_asr import Qwen3ASRModel
138
+
139
+ model = Qwen3ASRModel.from_pretrained(
140
+ "Qwen/Qwen3-ASR-1.7B",
141
+ dtype=torch.bfloat16,
142
+ device_map="cuda:0",
143
+ # attn_implementation="flash_attention_2",
144
+ max_inference_batch_size=32, # Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
145
+ max_new_tokens=256, # Maximum number of tokens to generate. Set a larger value for long audio input.
146
+ forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
147
+ forced_aligner_kwargs=dict(
148
+ dtype=torch.bfloat16,
149
+ device_map="cuda:0",
150
+ # attn_implementation="flash_attention_2",
151
+ ),
152
+ )
153
+
154
+ results = model.transcribe(
155
+ audio=[
156
+ "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
157
+ "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
158
+ ],
159
+ language=["Chinese", "English"], # can also be set to None for automatic language detection
160
+ return_time_stamps=True,
161
+ )
162
+
163
+ for r in results:
164
+ print(r.language, r.text, r.time_stamps[0])
165
+ ```
166
+
167
+ For more detailed usage examples, please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_asr_transformers.py) for the transformers backend.
168
+
169
+ #### vLLM Backend
170
+
171
+ If you want the fastest inference speed with Qwen3-ASR, we strongly recommend using the vLLM backend by initializing the model with `Qwen3ASRModel.LLM(...)`. Example code is provided below. Note that you must install it via `pip install -U qwen-asr[vllm]`. If you want the model to output timestamps, it’s best to install FlashAttention via `pip install -U flash-attn --no-build-isolation` to speed up inference for the forced aligner model. Remember to wrap your code under `if __name__ == '__main__':` to avoid the `spawn` error described in [vLLM Troubleshooting](https://docs.vllm.ai/en/latest/usage/troubleshooting/#python-multiprocessing).
172
+
173
+ ```python
174
+ import torch
175
+ from qwen_asr import Qwen3ASRModel
176
+
177
+ if __name__ == '__main__':
178
+ model = Qwen3ASRModel.LLM(
179
+ model="Qwen/Qwen3-ASR-1.7B",
180
+ gpu_memory_utilization=0.7,
181
+ max_inference_batch_size=128, # Batch size limit for inference. -1 means unlimited. Smaller values can help avoid OOM.
182
+ max_new_tokens=4096, # Maximum number of tokens to generate. Set a larger value for long audio input.
183
+ forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
184
+ forced_aligner_kwargs=dict(
185
+ dtype=torch.bfloat16,
186
+ device_map="cuda:0",
187
+ # attn_implementation="flash_attention_2",
188
+ ),
189
+ )
190
+
191
+ results = model.transcribe(
192
+ audio=[
193
+ "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
194
+ "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav",
195
+ ],
196
+ language=["Chinese", "English"], # can also be set to None for automatic language detection
197
+ return_time_stamps=True,
198
+ )
199
+
200
+ for r in results:
201
+ print(r.language, r.text, r.time_stamps[0])
202
+ ```
203
+
204
+ For more detailed usage examples, please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_asr_vllm.py) for the vLLM backend. In addition, you can start a vLLM server via the `qwen-asr-serve` command, which is a wrapper around `vllm serve`. You can pass any arguments supported by `vllm serve`, for example:
205
+
206
+ ```bash
207
+ qwen-asr-serve Qwen/Qwen3-ASR-1.7B --gpu-memory-utilization 0.8 --host 0.0.0.0 --port 8000
208
+ ```
209
+
210
+ And send requests to the server via:
211
+
212
+ ```python
213
+ import requests
214
+
215
+ url = "http://localhost:8000/v1/chat/completions"
216
+ headers = {"Content-Type": "application/json"}
217
+
218
+ data = {
219
+ "messages": [
220
+ {
221
+ "role": "user",
222
+ "content": [
223
+ {
224
+ "type": "audio_url",
225
+ "audio_url": {
226
+ "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
227
+ },
228
+ }
229
+ ],
230
+ }
231
+ ]
232
+ }
233
+
234
+ response = requests.post(url, headers=headers, json=data, timeout=300)
235
+ response.raise_for_status()
236
+ content = response.json()['choices'][0]['message']['content']
237
+ print(content)
238
+
239
+ # parse ASR output if you want
240
+ from qwen_asr import parse_asr_output
241
+ language, text = parse_asr_output(content)
242
+ print(language)
243
+ print(text)
244
+ ```
245
+
246
+ #### Streaming Inference
247
+
248
+ Qwen3-ASR fully supports streaming inference. Currently, streaming inference is only available with the vLLM backend. Note that streaming inference does not support batch inference or returning timestamps. Please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_asr_vllm_streaming.py) for details. You can also launch a streaming web demo through the [guide](#streaming-demo) to experience Qwen3-ASR’s streaming transcription capabilities.
249
+
250
+ #### ForcedAligner Usage
251
+
252
+ `Qwen3-ForcedAligner-0.6B` can align text–speech pairs and return word or character level timestamps. Here is an example of using the forced aligner directly:
253
+
254
+ ```python
255
+ import torch
256
+ from qwen_asr import Qwen3ForcedAligner
257
+
258
+ model = Qwen3ForcedAligner.from_pretrained(
259
+ "Qwen/Qwen3-ForcedAligner-0.6B",
260
+ dtype=torch.bfloat16,
261
+ device_map="cuda:0",
262
+ # attn_implementation="flash_attention_2",
263
+ )
264
+
265
+ results = model.align(
266
+ audio="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav",
267
+ text="甚至出现交易几乎停滞的情况。",
268
+ language="Chinese",
269
+ )
270
+
271
+ print(results[0])
272
+ print(results[0][0].text, results[0][0].start_time, results[0][0].end_time)
273
+ ```
274
+
275
+ In addition, the forced aligner supports local paths / URLs / base64 data / `(np.ndarray, sr)` inputs and batch inference. Please refer to the [example code](https://github.com/QwenLM/Qwen3-ASR/blob/main/examples/example_qwen3_forced_aligner.py) for details.
276
+
277
+ ### DashScope API Usage
278
+
279
+ To further explore Qwen3-ASR, we encourage you to try our DashScope API for a faster and more efficient experience. For detailed API information and documentation, please refer to the following:
280
+
281
+ | API Description | API Documentation (Mainland China) | API Documentation (International) |
282
+ |------------------|-----------------------------------|------------------------------------|
283
+ | Real-time API for Qwen3-ASR. | [https://help.aliyun.com/zh/model-studio/qwen-real-time-speech-recognition](https://help.aliyun.com/zh/model-studio/qwen-real-time-speech-recognition) | [https://www.alibabacloud.com/help/en/model-studio/qwen-real-time-speech-recognition](https://www.alibabacloud.com/help/en/model-studio/qwen-real-time-speech-recognition) |
284
+ | FileTrans API for Qwen3-ASR. | [https://help.aliyun.com/zh/model-studio/qwen-speech-recognition](https://help.aliyun.com/zh/model-studio/qwen-speech-recognition) | [https://www.alibabacloud.com/help/en/model-studio/qwen-speech-recognition](https://www.alibabacloud.com/help/en/model-studio/qwen-speech-recognition) |
285
+
286
+
287
+ ## Launch Local Web UI Demo
288
+
289
+ ### Gradio Demo
290
+
291
+ To launch the Qwen3-ASR web UI gradio demo, install the `qwen-asr` package and run `qwen-asr-demo`. Use the command below for help:
292
+
293
+ ```bash
294
+ qwen-asr-demo --help
295
+ ```
296
+
297
+ To launch the demo, you can use the following commands:
298
+
299
+ ```bash
300
+ # Transformers backend
301
+ qwen-asr-demo \
302
+ --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
303
+ --backend transformers \
304
+ --cuda-visible-devices 0 \
305
+ --ip 0.0.0.0 --port 8000
306
+
307
+ # Transformers backend + Forced Aligner (enable timestamps)
308
+ qwen-asr-demo \
309
+ --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
310
+ --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B \
311
+ --backend transformers \
312
+ --cuda-visible-devices 0 \
313
+ --backend-kwargs '{"device_map":"cuda:0","dtype":"bfloat16","max_inference_batch_size":8,"max_new_tokens":256}' \
314
+ --aligner-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}' \
315
+ --ip 0.0.0.0 --port 8000
316
+
317
+ # vLLM backend + Forced Aligner (enable timestamps)
318
+ qwen-asr-demo \
319
+ --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
320
+ --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B \
321
+ --backend vllm \
322
+ --cuda-visible-devices 0 \
323
+ --backend-kwargs '{"gpu_memory_utilization":0.7,"max_inference_batch_size":8,"max_new_tokens":2048}' \
324
+ --aligner-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}' \
325
+ --ip 0.0.0.0 --port 8000
326
+ ```
327
+
328
+ Then open `http://<your-ip>:8000`, or access it via port forwarding in tools like VS Code.
329
+
330
+ #### Backend Notes
331
+
332
+ This demo supports two backends: transformers and vLLM. All backend-specific initialization parameters should be passed via `--backend-kwargs` as a JSON dict. If not provided, the demo will use sensible defaults.
333
+
334
+ ```bash
335
+ # Example: override transformers init args without flash attention
336
+ --backend-kwargs '{"device_map":"cuda:0","dtype":"bfloat16"}'
337
+
338
+ # Example: override vLLM init args with 65% GPU memory
339
+ --backend-kwargs '{"gpu_memory_utilization":0.65}'
340
+ ```
341
+
342
+ #### CUDA Device Notes
343
+
344
+ Because vLLM does not follow `cuda:0` style device selection, this demo selects GPUs by setting `CUDA_VISIBLE_DEVICES` via `--cuda-visible-devices`.
345
+
346
+ ```bash
347
+ # Use GPU 0
348
+ --cuda-visible-devices 0
349
+
350
+ # Use GPU 1
351
+ --cuda-visible-devices 1
352
+ ```
353
+
354
+ #### Timestamps Notes
355
+
356
+ Timestamps are only available when `--aligner-checkpoint` is provided. If you launch the demo without a forced aligner, the timestamps UI will be hidden automatically.
357
+
358
+ ```bash
359
+ # No forced aligner
360
+ qwen-asr-demo --asr-checkpoint Qwen/Qwen3-ASR-1.7B
361
+
362
+ # With forced aligner
363
+ qwen-asr-demo \
364
+ --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
365
+ --aligner-checkpoint Qwen/Qwen3-ForcedAligner-0.6B
366
+ ```
367
+
368
+ #### HTTPS Notes
369
+
370
+ To avoid browser microphone permission issues after deploying the server, it is recommended/required to run the gradio service over HTTPS (especially when accessed remotely or behind modern browsers/gateways). Use `--ssl-certfile` and `--ssl-keyfile` to enable HTTPS. First, generate a private key and a self-signed certificate (valid for 365 days):
371
+
372
+ ```bash
373
+ openssl req -x509 -newkey rsa:2048 \
374
+ -keyout key.pem -out cert.pem \
375
+ -days 365 -nodes \
376
+ -subj "/CN=localhost"
377
+ ```
378
+
379
+ Then run the demo with HTTPS:
380
+
381
+ ```bash
382
+ qwen-asr-demo \
383
+ --asr-checkpoint Qwen/Qwen3-ASR-1.7B \
384
+ --backend transformers \
385
+ --cuda-visible-devices 0 \
386
+ --ip 0.0.0.0 --port 8000 \
387
+ --ssl-certfile cert.pem \
388
+ --ssl-keyfile key.pem \
389
+ --no-ssl-verify
390
+ ```
391
+
392
+ Then open `https://<your-ip>:8000` to use it. If your browser shows a warning, that’s expected for self-signed certificates. For production, use a real certificate.
393
+
394
+ ### Streaming Demo
395
+
396
+ To experience Qwen3-ASR’s streaming transcription capability in a web UI, we provide a minimal Flask-based streaming demo. The demo captures microphone audio in the browser, resamples it to 16,000 Hz, and continuously pushes PCM chunks to the model. Run the demo with the following command:
397
+
398
+ ```bash
399
+ qwen-asr-demo-streaming \
400
+ --asr-model-path Qwen/Qwen3-ASR-1.7B \
401
+ --host 0.0.0.0 \
402
+ --port 8000 \
403
+ --gpu-memory-utilization 0.9
404
+ ```
405
+
406
+ Then open `http://<your-ip>:8000`, or access it via port forwarding in tools like VS Code.
407
+
408
+ ## Deployment with vLLM
409
+
410
+ vLLM officially provides day-0 model support for Qwen3-ASR for efficient inference.
411
+
412
+ ### Installation
413
+ You can run Qwen3-ASR with vLLM nightly wheel or docker image. To install the nightly version of vLLM, we recommend using `uv` as the environment manager
414
+ ```bash
415
+ uv venv
416
+ source .venv/bin/activate
417
+ uv pip install -U vllm --pre \
418
+ --extra-index-url https://wheels.vllm.ai/nightly/cu129 \
419
+ --extra-index-url https://download.pytorch.org/whl/cu129 \
420
+ --index-strategy unsafe-best-match
421
+ uv pip install "vllm[audio]" # For additional audio dependencies
422
+ ```
423
+
424
+ ### Online Serving
425
+ You can easily deploy Qwen3-ASR with vLLM by running the following command
426
+ ```bash
427
+ vllm serve Qwen/Qwen3-ASR-1.7B
428
+ ```
429
+ After the model server is successfully deployed, you can interact with it in multiple ways.
430
+
431
+ #### Using OpenAI SDK
432
+ ```python
433
+ import base64
434
+ import httpx
435
+ from openai import OpenAI
436
+
437
+ # Initialize client
438
+ client = OpenAI(
439
+ base_url="http://localhost:8000/v1",
440
+ api_key="EMPTY"
441
+ )
442
+
443
+ # Create multimodal chat completion request
444
+ response = client.chat.completions.create(
445
+ model="Qwen/Qwen3-ASR-1.7B",
446
+ messages=[
447
+ {
448
+ "role": "user",
449
+ "content": [
450
+ {
451
+ "type": "audio_url",
452
+ "audio_url": {
453
+ {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"}
454
+ }
455
+ }
456
+ ]
457
+ }
458
+ ],
459
+ )
460
+
461
+ print(response.choices[0].message.content)
462
+ ```
463
+ This model is also supported on vLLM with OpenAI transcription API.
464
+ ```python
465
+ import httpx
466
+ from openai import OpenAI
467
+
468
+ # Initialize client
469
+ client = OpenAI(
470
+ base_url="http://localhost:8000/v1",
471
+ api_key="EMPTY"
472
+ )
473
+ audio_url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
474
+ audio_file = httpx.get(audio_url).content
475
+
476
+ transcription = client.audio.transcriptions.create(
477
+ model="Qwen/Qwen3-ASR-1.7B",
478
+ file=audio_file,
479
+ )
480
+
481
+ print(transcription.text)
482
+ ```
483
+
484
+ #### Using cURL
485
+ ```bash
486
+ curl http://localhost:8000/v1/chat/completions \
487
+ -H "Content-Type: application/json" \
488
+ -d '{
489
+ "messages": [
490
+ {"role": "user", "content": [
491
+ {"type": "audio_url", "audio_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"}}
492
+ ]}
493
+ ]
494
+ }'
495
+ ```
496
+
497
+ ### Offline Inference
498
+ See the following example on using vLLM to run offline inference with Qwen3-ASR
499
+ ```python
500
+ from vllm import LLM, SamplingParams
501
+ from vllm.assets.audio import AudioAsset
502
+ import base64
503
+ import requests
504
+
505
+ # Initialize the LLM
506
+ llm = LLM(
507
+ model="Qwen/Qwen3-ASR-1.7B"
508
+ )
509
+
510
+ # Load audio
511
+ audio_asset = AudioAsset("winning_call")
512
+
513
+ # Create conversation with audio content
514
+ conversation = [
515
+ {
516
+ "role": "user",
517
+ "content": [
518
+ {
519
+ "type": "audio_url",
520
+ "audio_url": {"url": audio_asset.url}
521
+ }
522
+ ]
523
+ }
524
+ ]
525
+
526
+ sampling_params = SamplingParams(temperature=0.01, max_tokens=256)
527
+
528
+ # Run inference using .chat()
529
+ outputs = llm.chat(conversation, sampling_params=sampling_params)
530
+ print(outputs[0].outputs[0].text)
531
+ ```
532
+
533
+
534
+ ## Docker
535
+
536
+ To make it easier to use our `qwen-asr` Python package, we provide a pre-built Docker image: [qwenllm/qwen3-asr](https://hub.docker.com/r/qwenllm/qwen3-asr). You only need to install the GPU driver and download the model files to run the code. Please follow the [NVIDIA Container Toolkit installation guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) to ensure Docker can access your GPU. If you are in Mainland China and have trouble reaching Docker Hub, you may use a registry mirror to accelerate image pulls.
537
+
538
+ First, pull the image and start a container:
539
+
540
+ ```bash
541
+ LOCAL_WORKDIR=/path/to/your/workspace
542
+ HOST_PORT=8000
543
+ CONTAINER_PORT=80
544
+ docker run --gpus all --name qwen3-asr \
545
+ -v /var/run/docker.sock:/var/run/docker.sock -p $HOST_PORT:$CONTAINER_PORT \
546
+ --mount type=bind,source=$LOCAL_WORKDIR,target=/data/shared/Qwen3-ASR \
547
+ --shm-size=4gb \
548
+ -it qwenllm/qwen3-asr:latest
549
+ ```
550
+
551
+ After running the command, you will enter the container’s bash shell. Your local workspace (**replace** `/path/to/your/workspace` **with the actual path**) will be mounted inside the container at `/data/shared/Qwen3-ASR`. Port `8000` on the host is mapped to port `80` in the container, so you can access services running in the container via `http://<host-ip>:8000`. Note that services inside the container must bind to `0.0.0.0` (not `127.0.0.1`) for port forwarding to work.
552
+
553
+ If you exit the container, you can start it again and re-enter it with:
554
+
555
+ ```bash
556
+ docker start qwen3-asr
557
+ docker exec -it qwen3-asr bash
558
+ ```
559
+
560
+ To remove the container completely, run:
561
+
562
+ ```bash
563
+ docker rm -f qwen3-asr
564
+ ```
565
+
566
+
567
+ ## Evaluation
568
+
569
+ During evaluation, we ran inference for all models with `dtype=torch.bfloat16` and set `max_new_tokens=1024` using vLLM. Greedy search was used for all decoding, and none of the tests specified a language parameter. The detailed evaluation results are shown below.
570
+
571
+ <details>
572
+ <summary>ASR Benchmarks on Public Datasets (WER ↓)</summary>
573
+
574
+ <table>
575
+ <thead>
576
+ <tr>
577
+ <th colspan="2" style="text-align: left;"></th>
578
+ <th style="text-align: center;">GPT-4o<br>-Transcribe</th>
579
+ <th style="text-align: center;">Gemini-2.5<br>-Pro</th>
580
+ <th style="text-align: center;">Doubao-ASR</th>
581
+ <th style="text-align: center;">Whisper<br>-large-v3</th>
582
+ <th style="text-align: center;">Fun-ASR<br>-MLT-Nano</th>
583
+ <th style="text-align: center;">Qwen3-ASR<br>-0.6B</th>
584
+ <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
585
+ </tr>
586
+ </thead>
587
+ <tbody>
588
+ <tr>
589
+ <td colspan="9" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">English (en)</td>
590
+ </tr>
591
+ <tr>
592
+ <td colspan="2" style="text-align: left;">Librispeech<br>clean | other</td>
593
+ <td style="text-align: center;"><strong>1.39</strong> | 3.75</td>
594
+ <td style="text-align: center;">2.89 | 3.56</td>
595
+ <td style="text-align: center;">2.78 | 5.70</td>
596
+ <td style="text-align: center;">1.51 | 3.97</td>
597
+ <td style="text-align: center;">1.68 | 4.03</td>
598
+ <td style="text-align: center;">2.11 | 4.55</td>
599
+ <td style="text-align: center;">1.63 | <strong>3.38</strong></td>
600
+ </tr>
601
+ <tr>
602
+ <td colspan="2" style="text-align: left;">GigaSpeech</td>
603
+ <td style="text-align: center;">25.50</td>
604
+ <td style="text-align: center;">9.37</td>
605
+ <td style="text-align: center;">9.55</td>
606
+ <td style="text-align: center;">9.76</td>
607
+ <td style="text-align: center;">-</td>
608
+ <td style="text-align: center;">8.88</td>
609
+ <td style="text-align: center;"><strong>8.45</strong></td>
610
+ </tr>
611
+ <tr>
612
+ <td colspan="2" style="text-align: left;">CV-en</td>
613
+ <td style="text-align: center;">9.08</td>
614
+ <td style="text-align: center;">14.49</td>
615
+ <td style="text-align: center;">13.78</td>
616
+ <td style="text-align: center;">9.90</td>
617
+ <td style="text-align: center;">9.90</td>
618
+ <td style="text-align: center;">9.92</td>
619
+ <td style="text-align: center;"><strong>7.39</strong></td>
620
+ </tr>
621
+ <tr>
622
+ <td colspan="2" style="text-align: left;">Fleurs-en</td>
623
+ <td style="text-align: center;"><strong>2.40</strong></td>
624
+ <td style="text-align: center;">2.94</td>
625
+ <td style="text-align: center;">6.31</td>
626
+ <td style="text-align: center;">4.08</td>
627
+ <td style="text-align: center;">5.49</td>
628
+ <td style="text-align: center;">4.39</td>
629
+ <td style="text-align: center;">3.35</td>
630
+ </tr>
631
+ <tr>
632
+ <td colspan="2" style="text-align: left;">MLS-en</td>
633
+ <td style="text-align: center;">5.12</td>
634
+ <td style="text-align: center;"><strong>3.68</strong></td>
635
+ <td style="text-align: center;">7.09</td>
636
+ <td style="text-align: center;">4.87</td>
637
+ <td style="text-align: center;">-</td>
638
+ <td style="text-align: center;">6.00</td>
639
+ <td style="text-align: center;">4.58</td>
640
+ </tr>
641
+ <tr>
642
+ <td colspan="2" style="text-align: left;">Tedlium</td>
643
+ <td style="text-align: center;">7.69</td>
644
+ <td style="text-align: center;">6.15</td>
645
+ <td style="text-align: center;">4.91</td>
646
+ <td style="text-align: center;">6.84</td>
647
+ <td style="text-align: center;">-</td>
648
+ <td style="text-align: center;"><strong>3.85<strong></td>
649
+ <td style="text-align: center;"><strong>4.50</strong></td>
650
+ </tr>
651
+ <tr>
652
+ <td colspan="2" style="text-align: left;">VoxPopuli</td>
653
+ <td style="text-align: center;">10.29</td>
654
+ <td style="text-align: center;">11.36</td>
655
+ <td style="text-align: center;">12.12</td>
656
+ <td style="text-align: center;">12.05</td>
657
+ <td style="text-align: center;">-</td>
658
+ <td style="text-align: center;"><strong>9.96<strong></td>
659
+ <td style="text-align: center;"><strong>9.15</strong></td>
660
+ </tr>
661
+ <tr>
662
+ <td colspan="9" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese (zh)</td>
663
+ </tr>
664
+ <tr>
665
+ <td colspan="2" style="text-align: left;">WenetSpeech<br>net | meeting</td>
666
+ <td style="text-align: center;">15.30 | 32.27</td>
667
+ <td style="text-align: center;">14.43 | 13.47</td>
668
+ <td style="text-align: center;">N/A</td>
669
+ <td style="text-align: center;">9.86 | 19.11</td>
670
+ <td style="text-align: center;">6.35 | -</td>
671
+ <td style="text-align: center;">5.97 | 6.88</td>
672
+ <td style="text-align: center;"><strong>4.97</strong> | <strong>5.88</strong></td>
673
+ </tr>
674
+ <tr>
675
+ <td colspan="2" style="text-align: left;">AISHELL-2-test</td>
676
+ <td style="text-align: center;">4.24</td>
677
+ <td style="text-align: center;">11.62</td>
678
+ <td style="text-align: center;">2.85</td>
679
+ <td style="text-align: center;">5.06</td>
680
+ <td style="text-align: center;">-</td>
681
+ <td style="text-align: center;">3.15</td>
682
+ <td style="text-align: center;"><strong>2.71</strong></td>
683
+ </tr>
684
+ <tr>
685
+ <td colspan="2" style="text-align: left;">SpeechIO</td>
686
+ <td style="text-align: center;">12.86</td>
687
+ <td style="text-align: center;">5.30</td>
688
+ <td style="text-align: center;">2.93</td>
689
+ <td style="text-align: center;">7.56</td>
690
+ <td style="text-align: center;">-</td>
691
+ <td style="text-align: center;">3.44</td>
692
+ <td style="text-align: center;"><strong>2.88</strong></td>
693
+ </tr>
694
+ <tr>
695
+ <td colspan="2" style="text-align: left;">Fleurs-zh</td>
696
+ <td style="text-align: center;">2.44</td>
697
+ <td style="text-align: center;">2.71</td>
698
+ <td style="text-align: center;">2.69</td>
699
+ <td style="text-align: center;">4.09</td>
700
+ <td style="text-align: center;">3.51</td>
701
+ <td style="text-align: center;">2.88</td>
702
+ <td style="text-align: center;"><strong>2.41</strong></td>
703
+ </tr>
704
+ <tr>
705
+ <td colspan="2" style="text-align: left;">CV-zh</td>
706
+ <td style="text-align: center;">6.32</td>
707
+ <td style="text-align: center;">7.70</td>
708
+ <td style="text-align: center;">5.95</td>
709
+ <td style="text-align: center;">12.91</td>
710
+ <td style="text-align: center;">6.20</td>
711
+ <td style="text-align: center;">6.89</td>
712
+ <td style="text-align: center;"><strong>5.35</strong></td>
713
+ </tr>
714
+ <tr>
715
+ <td colspan="9" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese Dialect</td>
716
+ </tr>
717
+ <tr>
718
+ <td colspan="2" style="text-align: left;">KeSpeech</td>
719
+ <td style="text-align: center;">26.87</td>
720
+ <td style="text-align: center;">24.71</td>
721
+ <td style="text-align: center;">5.27</td>
722
+ <td style="text-align: center;">28.79</td>
723
+ <td style="text-align: center;">-</td>
724
+ <td style="text-align: center;">7.08</td>
725
+ <td style="text-align: center;"><strong>5.10</strong></td>
726
+ </tr>
727
+ <tr>
728
+ <td colspan="2" style="text-align: left;">Fleurs-yue</td>
729
+ <td style="text-align: center;">4.98</td>
730
+ <td style="text-align: center;">9.43</td>
731
+ <td style="text-align: center;">4.98</td>
732
+ <td style="text-align: center;">9.18</td>
733
+ <td style="text-align: center;">-</td>
734
+ <td style="text-align: center;">5.79</td>
735
+ <td style="text-align: center;"><strong>3.98</strong></td>
736
+ </tr>
737
+ <tr>
738
+ <td colspan="2" style="text-align: left;">CV-yue</td>
739
+ <td style="text-align: center;">11.36</td>
740
+ <td style="text-align: center;">18.76</td>
741
+ <td style="text-align: center;">13.20</td>
742
+ <td style="text-align: center;">16.23</td>
743
+ <td style="text-align: center;">-</td>
744
+ <td style="text-align: center;">9.50</td>
745
+ <td style="text-align: center;"><strong>7.57</strong></td>
746
+ </tr>
747
+ <tr>
748
+ <td colspan="2" style="text-align: left;">CV-zh-tw</td>
749
+ <td style="text-align: center;">6.32</td>
750
+ <td style="text-align: center;">7.31</td>
751
+ <td style="text-align: center;">4.06</td>
752
+ <td style="text-align: center;">7.84</td>
753
+ <td style="text-align: center;">-</td>
754
+ <td style="text-align: center;">5.59</td>
755
+ <td style="text-align: center;"><strong>3.77</strong></td>
756
+ </tr>
757
+ <tr>
758
+ <td colspan="2" style="text-align: left;">WenetSpeech-Yue<br>short | long</td>
759
+ <td style="text-align: center;">15.62 | 25.29</td>
760
+ <td style="text-align: center;">25.19 | 11.23</td>
761
+ <td style="text-align: center;">9.74 | 11.40</td>
762
+ <td style="text-align: center;">32.26 | 46.64</td>
763
+ <td style="text-align: center;">- | -</td>
764
+ <td style="text-align: center;">7.54 | 9.92</td>
765
+ <td style="text-align: center;"><strong>5.82</strong> | <strong>8.85</strong></td>
766
+ </tr>
767
+ <tr>
768
+ <td colspan="2" style="text-align: left;">WenetSpeech-Chuan<br>easy | hard</td>
769
+ <td style="text-align: center;">34.81 | 53.98</td>
770
+ <td style="text-align: center;">43.79 | 67.30</td>
771
+ <td style="text-align: center;"><strong>11.40<strong> | <strong>20.20</strong></td>
772
+ <td style="text-align: center;">14.35 | 26.80</td>
773
+ <td style="text-align: center;">- | -</td>
774
+ <td style="text-align: center;">13.92 | 24.45</td>
775
+ <td style="text-align: center;">11.99 | 21.63</td>
776
+ </tr>
777
+ </tbody>
778
+ </table>
779
+
780
+ </details>
781
+
782
+ <details>
783
+ <summary>ASR Benchmarks on Internal Datasets (WER ↓)</summary>
784
+
785
+ <table>
786
+ <thead>
787
+ <tr>
788
+ <th style="text-align: left;"></th>
789
+ <th style="text-align: center;">GPT-4o<br>-Transcribe</th>
790
+ <th style="text-align: center;">Gemini-2.5<br>-Pro</th>
791
+ <th style="text-align: center;">Doubao-ASR</th>
792
+ <th style="text-align: center;">Whisper<br>-large-v3</th>
793
+ <th style="text-align: center;">Fun-ASR<br>-MLT-Nano</th>
794
+ <th style="text-align: center;">Qwen3-ASR<br>-0.6B</th>
795
+ <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
796
+ </tr>
797
+ </thead>
798
+ <tbody>
799
+ <tr>
800
+ <td colspan="8" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Accented English</td>
801
+ </tr>
802
+ <tr>
803
+ <td style="text-align: left;">Dialog-Accented English</td>
804
+ <td style="text-align: center;">28.56</td>
805
+ <td style="text-align: center;">23.85</td>
806
+ <td style="text-align: center;">20.41</td>
807
+ <td style="text-align: center;">21.30</td>
808
+ <td style="text-align: center;">19.96</td>
809
+ <td style="text-align: center;"><strong>16.62<strong></td>
810
+ <td style="text-align: center;"><strong>16.07</strong></td>
811
+ </tr>
812
+ <tr>
813
+ <td colspan="8" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese Mandarin</td>
814
+ </tr>
815
+ <tr>
816
+ <td style="text-align: left;">Elders&Kids</td>
817
+ <td style="text-align: center;">14.27</td>
818
+ <td style="text-align: center;">36.93</td>
819
+ <td style="text-align: center;">4.17</td>
820
+ <td style="text-align: center;">10.61</td>
821
+ <td style="text-align: center;">4.54</td>
822
+ <td style="text-align: center;">4.48</td>
823
+ <td style="text-align: center;"><strong>3.81</strong></td>
824
+ </tr>
825
+ <tr>
826
+ <td style="text-align: left;">ExtremeNoise</td>
827
+ <td style="text-align: center;">36.11</td>
828
+ <td style="text-align: center;">29.06</td>
829
+ <td style="text-align: center;">17.04</td>
830
+ <td style="text-align: center;">63.17</td>
831
+ <td style="text-align: center;">36.55</td>
832
+ <td style="text-align: center;">17.88</td>
833
+ <td style="text-align: center;"><strong>16.17</strong></td>
834
+ </tr>
835
+ <tr>
836
+ <td style="text-align: left;">TongueTwister</td>
837
+ <td style="text-align: center;">20.87</td>
838
+ <td style="text-align: center;">4.97</td>
839
+ <td style="text-align: center;">3.47</td>
840
+ <td style="text-align: center;">16.63</td>
841
+ <td style="text-align: center;">9.02</td>
842
+ <td style="text-align: center;">4.06</td>
843
+ <td style="text-align: center;"><strong>2.44</strong></td>
844
+ </tr>
845
+ <tr>
846
+ <td style="text-align: left;">Dialog-Mandarin</td>
847
+ <td style="text-align: center;">20.73</td>
848
+ <td style="text-align: center;">12.50</td>
849
+ <td style="text-align: center;">6.61</td>
850
+ <td style="text-align: center;">14.01</td>
851
+ <td style="text-align: center;">7.32</td>
852
+ <td style="text-align: center;">7.06</td>
853
+ <td style="text-align: center;"><strong>6.54</strong></td>
854
+ </tr>
855
+ <tr>
856
+ <td colspan="8" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Chinese Dialect</td>
857
+ </tr>
858
+ <tr>
859
+ <td style="text-align: left;">Dialog-Cantonese</td>
860
+ <td style="text-align: center;">16.05</td>
861
+ <td style="text-align: center;">14.98</td>
862
+ <td style="text-align: center;">7.56</td>
863
+ <td style="text-align: center;">31.04</td>
864
+ <td style="text-align: center;">5.85</td>
865
+ <td style="text-align: center;"><strong>4.80<strong></td>
866
+ <td style="text-align: center;"><strong>4.12</strong></td>
867
+ </tr>
868
+ <tr>
869
+ <td style="text-align: left;">Dialog-Chinese Dialects</td>
870
+ <td style="text-align: center;">45.37</td>
871
+ <td style="text-align: center;">47.70</td>
872
+ <td style="text-align: center;">19.85</td>
873
+ <td style="text-align: center;">44.55</td>
874
+ <td style="text-align: center;">19.41</td>
875
+ <td style="text-align: center;"><strong>18.24<strong></td>
876
+ <td style="text-align: center;"><strong>15.94</strong></td>
877
+ </tr>
878
+ </tbody>
879
+ </table>
880
+ <p><strong>Dialect coverage:</strong> Results for <em>Dialog-Accented English</em> are averaged over 16 accents, and results for <em>Dialog-Chinese Dialects</em> are averaged over 22 Chinese dialects.</p>
881
+
882
+ </details>
883
+
884
+ <details>
885
+ <summary>Multilingual ASR Benchmarks (WER ↓)</summary>
886
+
887
+ <table>
888
+ <thead>
889
+ <tr>
890
+ <th style="text-align: left;"></th>
891
+ <th style="text-align: center;">GLM-ASR<br>-Nano-2512</th>
892
+ <th style="text-align: center;">Whisper<br>-large-v3</th>
893
+ <th style="text-align: center;">Fun-ASR<br>-MLT-Nano</th>
894
+ <th style="text-align: center;">Qwen3-ASR<br>-0.6B</th>
895
+ <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
896
+ </tr>
897
+ </thead>
898
+ <tbody>
899
+ <tr>
900
+ <td colspan="6" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Open-sourced Benchmarks</td>
901
+ </tr>
902
+ <tr>
903
+ <td style="text-align: left;">MLS</td>
904
+ <td style="text-align: center;">13.32</td>
905
+ <td style="text-align: center;">8.62</td>
906
+ <td style="text-align: center;">28.70</td>
907
+ <td style="text-align: center;">13.19</td>
908
+ <td style="text-align: center;"><strong>8.55</strong></td>
909
+ </tr>
910
+ <tr>
911
+ <td style="text-align: left;">CommonVoice</td>
912
+ <td style="text-align: center;">19.40</td>
913
+ <td style="text-align: center;">10.77</td>
914
+ <td style="text-align: center;">17.25</td>
915
+ <td style="text-align: center;">12.75</td>
916
+ <td style="text-align: center;"><strong>9.18</strong></td>
917
+ </tr>
918
+ <tr>
919
+ <td style="text-align: left;">MLC-SLM</td>
920
+ <td style="text-align: center;">34.93</td>
921
+ <td style="text-align: center;">15.68</td>
922
+ <td style="text-align: center;">29.94</td>
923
+ <td style="text-align: center;">15.84</td>
924
+ <td style="text-align: center;"><strong>12.74</strong></td>
925
+ </tr>
926
+ <tr>
927
+ <td style="text-align: left;">Fleurs</td>
928
+ <td style="text-align: center;">16.08</td>
929
+ <td style="text-align: center;">5.27</td>
930
+ <td style="text-align: center;">10.03</td>
931
+ <td style="text-align: center;">7.57</td>
932
+ <td style="text-align: center;"><strong>4.90</strong></td>
933
+ </tr>
934
+ <tr>
935
+ <td style="text-align: left;">Fleurs<sup>†</sup></td>
936
+ <td style="text-align: center;">20.05</td>
937
+ <td style="text-align: center;">6.85</td>
938
+ <td style="text-align: center;">31.89</td>
939
+ <td style="text-align: center;">10.37</td>
940
+ <td style="text-align: center;"><strong>6.62</strong></td>
941
+ </tr>
942
+ <tr>
943
+ <td style="text-align: left;">Fleurs<sup>††</sup></td>
944
+ <td style="text-align: center;">24.83</td>
945
+ <td style="text-align: center;"><strong>8.16</strong></td>
946
+ <td style="text-align: center;">47.84</td>
947
+ <td style="text-align: center;">21.80</td>
948
+ <td style="text-align: center;">12.60</td>
949
+ </tr>
950
+ <tr>
951
+ <td colspan="6" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Qwen-ASR Internal Benchmarks</td>
952
+ </tr>
953
+ <tr>
954
+ <td style="text-align: left;">News-Multilingual</td>
955
+ <td style="text-align: center;">49.40</td>
956
+ <td style="text-align: center;">14.80</td>
957
+ <td style="text-align: center;">65.07</td>
958
+ <td style="text-align: center;">17.39</td>
959
+ <td style="text-align: center;"><strong>12.80</strong></td>
960
+ </tr>
961
+ </tbody>
962
+ </table>
963
+ <p><strong>Language coverage:</strong> <em>MLS</em> includes 8 languages: {da, de, en, es, fr, it, pl, pt}.<br><em>CommonVoice</em> includes 13 languages: {en, zh, yue, zh_TW, ar, de, es, fr, it, ja, ko, pt, ru}.<br><em>MLC-SLM</em> includes 11 languages: {en, fr, de, it, pt, es, ja, ko, ru, th, vi}.<br><em>Fleurs</em> includes 12 languages: {en, zh, yue, ar, de, es, fr, it, ja, ko, pt, ru }.<br><em>Fleurs<sup>†</sup></em> includes 8 additional languages beyond Fleurs: {hi, id, ms, nl, pl, th, tr, vi}.<br><em>Fleurs<sup>††</sup></em> includes 10 additional languages beyond Fleurs<sup>†</sup>: {cs, da, el, fa, fi, fil, hu, mk, ro, sv}.<br><em>News-Multilingual</em> includes 15 languages: {ar, de, es, fr, hi, id, it, ja, ko, nl, pl, pt, ru, th, vi}.</p>
964
+
965
+ </details>
966
+
967
+ <details>
968
+ <summary>Language Identification Accuracy (%) ↑</summary>
969
+
970
+ <table>
971
+ <thead>
972
+ <tr>
973
+ <th style="text-align: left;"></th>
974
+ <th style="text-align: center;">Whisper-large-v3</th>
975
+ <th style="text-align: center;">Qwen3-ASR-0.6B</th>
976
+ <th style="text-align: center;">Qwen3-ASR-1.7B</th>
977
+ </tr>
978
+ </thead>
979
+ <tbody>
980
+ <tr>
981
+ <td style="text-align: left;">MLS</td>
982
+ <td style="text-align: center;"><strong>99.9</strong></td>
983
+ <td style="text-align: center;">99.3</td>
984
+ <td style="text-align: center;"><strong>99.9</strong></td>
985
+ </tr>
986
+ <tr>
987
+ <td style="text-align: left;">CommonVoice</td>
988
+ <td style="text-align: center;">92.7</td>
989
+ <td style="text-align: center;"><strong>98.2<strong></td>
990
+ <td style="text-align: center;"><strong>98.7</strong></td>
991
+ </tr>
992
+ <tr>
993
+ <td style="text-align: left;">MLC-SLM</td>
994
+ <td style="text-align: center;">89.2</td>
995
+ <td style="text-align: center;"><strong>92.7<strong></td>
996
+ <td style="text-align: center;"><strong>94.1</strong></td>
997
+ </tr>
998
+ <tr>
999
+ <td style="text-align: left;">Fleurs</td>
1000
+ <td style="text-align: center;">94.6</td>
1001
+ <td style="text-align: center;"><strong>97.1<strong></td>
1002
+ <td style="text-align: center;"><strong>98.7</strong></td>
1003
+ </tr>
1004
+ <tr style="border-top: 1px solid #ddd;">
1005
+ <td style="text-align: left;"><em>Avg.</em></td>
1006
+ <td style="text-align: center;">94.1</td>
1007
+ <td style="text-align: center;"><strong>96.8<strong></td>
1008
+ <td style="text-align: center;"><strong>97.9</strong></td>
1009
+ </tr>
1010
+ </tbody>
1011
+ </table>
1012
+ <p><strong>Language coverage:</strong> The language sets follow Multilingual ASR Benchmarks. Here, Fleurs corresponds to Fleurs<sup>††</sup> in Multilingual ASR Benchmarks and covers 30 languages.</p>
1013
+
1014
+ </details>
1015
+
1016
+ <details>
1017
+ <summary>Singing Voice & Song Transcription (WER ↓)</summary>
1018
+
1019
+ <table>
1020
+ <thead>
1021
+ <tr>
1022
+ <th style="text-align: left;"></th>
1023
+ <th style="text-align: center;">GPT-4o<br>-Transcribe</th>
1024
+ <th style="text-align: center;">Gemini-2.5<br>-Pro</th>
1025
+ <th style="text-align: center;">Doubao-ASR<br>-1.0</th>
1026
+ <th style="text-align: center;">Whisper<br>-large-v3</th>
1027
+ <th style="text-align: center;">Fun-ASR-MLT<br>-Nano</th>
1028
+ <th style="text-align: center;">Qwen3-ASR<br>-1.7B</th>
1029
+ </tr>
1030
+ </thead>
1031
+ <tbody>
1032
+ <tr>
1033
+ <td colspan="7" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Singing</td>
1034
+ </tr>
1035
+ <tr>
1036
+ <td style="text-align: left;">M4Singer</td>
1037
+ <td style="text-align: center;">16.77</td>
1038
+ <td style="text-align: center;">20.88</td>
1039
+ <td style="text-align: center;">7.88</td>
1040
+ <td style="text-align: center;">13.58</td>
1041
+ <td style="text-align: center;">7.29</td>
1042
+ <td style="text-align: center;"><strong>5.98</strong></td>
1043
+ </tr>
1044
+ <tr>
1045
+ <td style="text-align: left;">MIR-1k-vocal</td>
1046
+ <td style="text-align: center;">11.87</td>
1047
+ <td style="text-align: center;">9.85</td>
1048
+ <td style="text-align: center;">6.56</td>
1049
+ <td style="text-align: center;">11.71</td>
1050
+ <td style="text-align: center;">8.17</td>
1051
+ <td style="text-align: center;"><strong>6.25</strong></td>
1052
+ </tr>
1053
+ <tr>
1054
+ <td style="text-align: left;">Opencpop</td>
1055
+ <td style="text-align: center;">7.93</td>
1056
+ <td style="text-align: center;">6.49</td>
1057
+ <td style="text-align: center;">3.80</td>
1058
+ <td style="text-align: center;">9.52</td>
1059
+ <td style="text-align: center;"><strong>2.98</strong></td>
1060
+ <td style="text-align: center;">3.08</td>
1061
+ </tr>
1062
+ <tr>
1063
+ <td style="text-align: left;">Popcs</td>
1064
+ <td style="text-align: center;">32.84</td>
1065
+ <td style="text-align: center;">15.13</td>
1066
+ <td style="text-align: center;">8.97</td>
1067
+ <td style="text-align: center;">13.77</td>
1068
+ <td style="text-align: center;">9.42</td>
1069
+ <td style="text-align: center;"><strong>8.52</strong></td>
1070
+ </tr>
1071
+ <tr>
1072
+ <td colspan="7" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Songs with BGM</td>
1073
+ </tr>
1074
+ <tr>
1075
+ <td style="text-align: left;">EntireSongs-en</td>
1076
+ <td style="text-align: center;">30.71</td>
1077
+ <td style="text-align: center;"><strong>12.18</strong></td>
1078
+ <td style="text-align: center;">33.51</td>
1079
+ <td style="text-align: center;">N/A</td>
1080
+ <td style="text-align: center;">N/A</td>
1081
+ <td style="text-align: center;">14.60</td>
1082
+ </tr>
1083
+ <tr>
1084
+ <td style="text-align: left;">EntireSongs-zh</td>
1085
+ <td style="text-align: center;">34.86</td>
1086
+ <td style="text-align: center;">18.68</td>
1087
+ <td style="text-align: center;">23.99</td>
1088
+ <td style="text-align: center;">N/A</td>
1089
+ <td style="text-align: center;">N/A</td>
1090
+ <td style="text-align: center;"><strong>13.91</strong></td>
1091
+ </tr>
1092
+ </tbody>
1093
+ </table>
1094
+
1095
+ </details>
1096
+
1097
+ <details>
1098
+ <summary>ASR Inference Mode Performance (WER ↓)</summary>
1099
+
1100
+ <table>
1101
+ <thead>
1102
+ <tr>
1103
+ <th style="text-align: left;">Model</th>
1104
+ <th style="text-align: left;">Infer. Mode</th>
1105
+ <th style="text-align: center;">Librispeech</th>
1106
+ <th style="text-align: center;">Fleurs-en</th>
1107
+ <th style="text-align: center;">Fleurs-zh</th>
1108
+ <th style="text-align: center;">Avg.</th>
1109
+ </tr>
1110
+ </thead>
1111
+ <tbody>
1112
+ <tr>
1113
+ <td rowspan="2" style="text-align: left; vertical-align: middle;">Qwen3-ASR-1.7B</td>
1114
+ <td style="text-align: left;">Offline</td>
1115
+ <td style="text-align: center;">1.63 | 3.38</td>
1116
+ <td style="text-align: center;">3.35</td>
1117
+ <td style="text-align: center;">2.41</td>
1118
+ <td style="text-align: center;">2.69</td>
1119
+ </tr>
1120
+ <tr>
1121
+ <td style="text-align: left;">Streaming</td>
1122
+ <td style="text-align: center;">1.95 | 4.51</td>
1123
+ <td style="text-align: center;">4.02</td>
1124
+ <td style="text-align: center;">2.84</td>
1125
+ <td style="text-align: center;">3.33</td>
1126
+ </tr>
1127
+ <tr style="border-top: 1px solid #ddd;">
1128
+ <td rowspan="2" style="text-align: left; vertical-align: middle;">Qwen3-ASR-0.6B</td>
1129
+ <td style="text-align: left;">Offline</td>
1130
+ <td style="text-align: center;">2.11 | 4.55</td>
1131
+ <td style="text-align: center;">4.39</td>
1132
+ <td style="text-align: center;">2.88</td>
1133
+ <td style="text-align: center;">3.48</td>
1134
+ </tr>
1135
+ <tr>
1136
+ <td style="text-align: left;">Streaming</td>
1137
+ <td style="text-align: center;">2.54 | 6.27</td>
1138
+ <td style="text-align: center;">5.38</td>
1139
+ <td style="text-align: center;">3.40</td>
1140
+ <td style="text-align: center;">4.40</td>
1141
+ </tr>
1142
+ </tbody>
1143
+ </table>
1144
+
1145
+ </details>
1146
+
1147
+ <details>
1148
+ <summary>Forced Alignment Benchmarks (AAS ms ↓)</summary>
1149
+
1150
+ <table>
1151
+ <thead>
1152
+ <tr>
1153
+ <th style="text-align: left;"></th>
1154
+ <th style="text-align: center;">Monotonic-Aligner</th>
1155
+ <th style="text-align: center;">NFA</th>
1156
+ <th style="text-align: center;">WhisperX</th>
1157
+ <th style="text-align: center;">Qwen3-ForcedAligner-0.6B</th>
1158
+ </tr>
1159
+ </thead>
1160
+ <tbody>
1161
+ <tr>
1162
+ <td colspan="5" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">MFA-Labeled Raw</td>
1163
+ </tr>
1164
+ <tr>
1165
+ <td style="text-align: left;">Chinese</td>
1166
+ <td style="text-align: center;">161.1</td>
1167
+ <td style="text-align: center;">109.8</td>
1168
+ <td style="text-align: center;">-</td>
1169
+ <td style="text-align: center;"><strong>33.1</strong></td>
1170
+ </tr>
1171
+ <tr>
1172
+ <td style="text-align: left;">English</td>
1173
+ <td style="text-align: center;">-</td>
1174
+ <td style="text-align: center;">107.5</td>
1175
+ <td style="text-align: center;">92.1</td>
1176
+ <td style="text-align: center;"><strong>37.5</strong></td>
1177
+ </tr>
1178
+ <tr>
1179
+ <td style="text-align: left;">French</td>
1180
+ <td style="text-align: center;">-</td>
1181
+ <td style="text-align: center;">100.7</td>
1182
+ <td style="text-align: center;">145.3</td>
1183
+ <td style="text-align: center;"><strong>41.7</strong></td>
1184
+ </tr>
1185
+ <tr>
1186
+ <td style="text-align: left;">German</td>
1187
+ <td style="text-align: center;">-</td>
1188
+ <td style="text-align: center;">122.7</td>
1189
+ <td style="text-align: center;">165.1</td>
1190
+ <td style="text-align: center;"><strong>46.5</strong></td>
1191
+ </tr>
1192
+ <tr>
1193
+ <td style="text-align: left;">Italian</td>
1194
+ <td style="text-align: center;">-</td>
1195
+ <td style="text-align: center;">142.7</td>
1196
+ <td style="text-align: center;">155.5</td>
1197
+ <td style="text-align: center;"><strong>75.5</strong></td>
1198
+ </tr>
1199
+ <tr>
1200
+ <td style="text-align: left;">Japanese</td>
1201
+ <td style="text-align: center;">-</td>
1202
+ <td style="text-align: center;">-</td>
1203
+ <td style="text-align: center;">-</td>
1204
+ <td style="text-align: center;"><strong>42.2</strong></td>
1205
+ </tr>
1206
+ <tr>
1207
+ <td style="text-align: left;">Korean</td>
1208
+ <td style="text-align: center;">-</td>
1209
+ <td style="text-align: center;">-</td>
1210
+ <td style="text-align: center;">-</td>
1211
+ <td style="text-align: center;"><strong>37.2</strong></td>
1212
+ </tr>
1213
+ <tr>
1214
+ <td style="text-align: left;">Portuguese</td>
1215
+ <td style="text-align: center;">-</td>
1216
+ <td style="text-align: center;">-</td>
1217
+ <td style="text-align: center;">-</td>
1218
+ <td style="text-align: center;"><strong>38.4</strong></td>
1219
+ </tr>
1220
+ <tr>
1221
+ <td style="text-align: left;">Russian</td>
1222
+ <td style="text-align: center;">-</td>
1223
+ <td style="text-align: center;">200.7</td>
1224
+ <td style="text-align: center;">-</td>
1225
+ <td style="text-align: center;"><strong>40.2</strong></td>
1226
+ </tr>
1227
+ <tr>
1228
+ <td style="text-align: left;">Spanish</td>
1229
+ <td style="text-align: center;">-</td>
1230
+ <td style="text-align: center;">124.7</td>
1231
+ <td style="text-align: center;">108.0</td>
1232
+ <td style="text-align: center;"><strong>36.8</strong></td>
1233
+ </tr>
1234
+ <tr>
1235
+ <td style="text-align: left;"><em>Avg.</em></td>
1236
+ <td style="text-align: center;">161.1</td>
1237
+ <td style="text-align: center;">129.8</td>
1238
+ <td style="text-align: center;">133.2</td>
1239
+ <td style="text-align: center;"><strong>42.9</strong></td>
1240
+ </tr>
1241
+ <tr>
1242
+ <td colspan="5" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">MFA-Labeled Concat-300s</td>
1243
+ </tr>
1244
+ <tr>
1245
+ <td style="text-align: left;">Chinese</td>
1246
+ <td style="text-align: center;">1742.4</td>
1247
+ <td style="text-align: center;">235.0</td>
1248
+ <td style="text-align: center;">-</td>
1249
+ <td style="text-align: center;"><strong>36.5</strong></td>
1250
+ </tr>
1251
+ <tr>
1252
+ <td style="text-align: left;">English</td>
1253
+ <td style="text-align: center;">-</td>
1254
+ <td style="text-align: center;">226.7</td>
1255
+ <td style="text-align: center;">227.2</td>
1256
+ <td style="text-align: center;"><strong>58.6</strong></td>
1257
+ </tr>
1258
+ <tr>
1259
+ <td style="text-align: left;">French</td>
1260
+ <td style="text-align: center;">-</td>
1261
+ <td style="text-align: center;">230.6</td>
1262
+ <td style="text-align: center;">2052.2</td>
1263
+ <td style="text-align: center;"><strong>53.4</strong></td>
1264
+ </tr>
1265
+ <tr>
1266
+ <td style="text-align: left;">German</td>
1267
+ <td style="text-align: center;">-</td>
1268
+ <td style="text-align: center;">220.3</td>
1269
+ <td style="text-align: center;">993.4</td>
1270
+ <td style="text-align: center;"><strong>62.4</strong></td>
1271
+ </tr>
1272
+ <tr>
1273
+ <td style="text-align: left;">Italian</td>
1274
+ <td style="text-align: center;">-</td>
1275
+ <td style="text-align: center;">290.5</td>
1276
+ <td style="text-align: center;">5719.4</td>
1277
+ <td style="text-align: center;"><strong>81.6</strong></td>
1278
+ </tr>
1279
+ <tr>
1280
+ <td style="text-align: left;">Japanese</td>
1281
+ <td style="text-align: center;">-</td>
1282
+ <td style="text-align: center;">-</td>
1283
+ <td style="text-align: center;">-</td>
1284
+ <td style="text-align: center;"><strong>81.3</strong></td>
1285
+ </tr>
1286
+ <tr>
1287
+ <td style="text-align: left;">Korean</td>
1288
+ <td style="text-align: center;">-</td>
1289
+ <td style="text-align: center;">-</td>
1290
+ <td style="text-align: center;">-</td>
1291
+ <td style="text-align: center;"><strong>42.2</strong></td>
1292
+ </tr>
1293
+ <tr>
1294
+ <td style="text-align: left;">Portuguese</td>
1295
+ <td style="text-align: center;">-</td>
1296
+ <td style="text-align: center;">-</td>
1297
+ <td style="text-align: center;">-</td>
1298
+ <td style="text-align: center;"><strong>50.0</strong></td>
1299
+ </tr>
1300
+ <tr>
1301
+ <td style="text-align: left;">Russian</td>
1302
+ <td style="text-align: center;">-</td>
1303
+ <td style="text-align: center;">283.3</td>
1304
+ <td style="text-align: center;">-</td>
1305
+ <td style="text-align: center;"><strong>43.0</strong></td>
1306
+ </tr>
1307
+ <tr>
1308
+ <td style="text-align: left;">Spanish</td>
1309
+ <td style="text-align: center;">-</td>
1310
+ <td style="text-align: center;">240.2</td>
1311
+ <td style="text-align: center;">4549.9</td>
1312
+ <td style="text-align: center;"><strong>39.6</strong></td>
1313
+ </tr>
1314
+ <tr>
1315
+ <td style="text-align: left;">Cross-lingual</td>
1316
+ <td style="text-align: center;">-</td>
1317
+ <td style="text-align: center;">-</td>
1318
+ <td style="text-align: center;">-</td>
1319
+ <td style="text-align: center;"><strong>34.2</strong></td>
1320
+ </tr>
1321
+ <tr>
1322
+ <td style="text-align: left;"><em>Avg.</em></td>
1323
+ <td style="text-align: center;">1742.4</td>
1324
+ <td style="text-align: center;">246.7</td>
1325
+ <td style="text-align: center;">2708.4</td>
1326
+ <td style="text-align: center;"><strong>52.9</strong></td>
1327
+ </tr>
1328
+ <tr>
1329
+ <td colspan="5" style="text-align: left; font-style: italic; border-top: 1px solid #ddd; border-bottom: 1px solid #ddd;">Human-Labeled</td>
1330
+ </tr>
1331
+ <tr>
1332
+ <td style="text-align: left;">Raw</td>
1333
+ <td style="text-align: center;">49.9</td>
1334
+ <td style="text-align: center;">88.6</td>
1335
+ <td style="text-align: center;">-</td>
1336
+ <td style="text-align: center;"><strong>27.8</strong></td>
1337
+ </tr>
1338
+ <tr>
1339
+ <td style="text-align: left;">Raw-Noisy</td>
1340
+ <td style="text-align: center;">53.3</td>
1341
+ <td style="text-align: center;">89.5</td>
1342
+ <td style="text-align: center;">-</td>
1343
+ <td style="text-align: center;"><strong>41.8</strong></td>
1344
+ </tr>
1345
+ <tr>
1346
+ <td style="text-align: left;">Concat-60s</td>
1347
+ <td style="text-align: center;">51.1</td>
1348
+ <td style="text-align: center;">86.7</td>
1349
+ <td style="text-align: center;">-</td>
1350
+ <td style="text-align: center;"><strong>25.3</strong></td>
1351
+ </tr>
1352
+ <tr>
1353
+ <td style="text-align: left;">Concat-300s</td>
1354
+ <td style="text-align: center;">410.8</td>
1355
+ <td style="text-align: center;">140.0</td>
1356
+ <td style="text-align: center;">-</td>
1357
+ <td style="text-align: center;"><strong>24.8</strong></td>
1358
+ </tr>
1359
+ <tr>
1360
+ <td style="text-align: left;">Concat-Cross-lingual</td>
1361
+ <td style="text-align: center;">-</td>
1362
+ <td style="text-align: center;">-</td>
1363
+ <td style="text-align: center;">-</td>
1364
+ <td style="text-align: center;"><strong>42.5</strong></td>
1365
+ </tr>
1366
+ <tr>
1367
+ <td style="text-align: left;"><em>Avg.</em></td>
1368
+ <td style="text-align: center;">141.3</td>
1369
+ <td style="text-align: center;">101.2</td>
1370
+ <td style="text-align: center;">-</td>
1371
+ <td style="text-align: center;"><strong>32.4</strong></td>
1372
+ </tr>
1373
+ </tbody>
1374
+ </table>
1375
+
1376
+ </details>
1377
+
1378
+
1379
+ ## Citation
1380
+
1381
+ If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil: :)
1382
+
1383
+ ```BibTeX
1384
+ @article{Qwen3-ASR,
1385
+ title={Qwen3-ASR Technical Report},
1386
+ author={Xian Shi, Xiong Wang, Zhifang Guo, Yongqi Wang, Pei Zhang, Xinyu Zhang, Zishan Guo, Hongkun Hao, Yu Xi, Baosong Yang, Jin Xu, Jingren Zhou, Junyang Lin},
1387
+ journal={arXiv preprint arXiv:2601.21337},
1388
+ year={2026}
1389
+ }
1390
+ ```
1391
+
1392
+
1393
+ <br>
models/Qwen3-ASR-0.6B/chat_template.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"}
models/Qwen3-ASR-0.6B/config.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ASRForConditionalGeneration"
4
+ ],
5
+ "model_type": "qwen3_asr",
6
+ "support_languages": [
7
+ "Chinese",
8
+ "English",
9
+ "Cantonese",
10
+ "Arabic",
11
+ "German",
12
+ "French",
13
+ "Spanish",
14
+ "Portuguese",
15
+ "Indonesian",
16
+ "Italian",
17
+ "Korean",
18
+ "Russian",
19
+ "Thai",
20
+ "Vietnamese",
21
+ "Japanese",
22
+ "Turkish",
23
+ "Hindi",
24
+ "Malay",
25
+ "Dutch",
26
+ "Swedish",
27
+ "Danish",
28
+ "Finnish",
29
+ "Polish",
30
+ "Czech",
31
+ "Filipino",
32
+ "Persian",
33
+ "Greek",
34
+ "Romanian",
35
+ "Hungarian",
36
+ "Macedonian"
37
+ ],
38
+ "thinker_config": {
39
+ "model_type": "qwen3_asr",
40
+ "architectures": [
41
+ "Qwen3ASRForConditionalGeneration"
42
+ ],
43
+ "audio_config": {
44
+ "_name_or_path": "",
45
+ "activation_dropout": 0,
46
+ "activation_function": "gelu",
47
+ "add_cross_attention": false,
48
+ "architectures": null,
49
+ "attention_dropout": 0,
50
+ "bad_words_ids": null,
51
+ "begin_suppress_tokens": null,
52
+ "bos_token_id": null,
53
+ "chunk_size_feed_forward": 0,
54
+ "conv_chunksize": 500,
55
+ "cross_attention_hidden_size": null,
56
+ "d_model": 896,
57
+ "decoder_start_token_id": null,
58
+ "diversity_penalty": 0.0,
59
+ "do_sample": false,
60
+ "downsample_hidden_size": 480,
61
+ "dropout": 0,
62
+ "dtype": null,
63
+ "early_stopping": false,
64
+ "encoder_attention_heads": 14,
65
+ "encoder_ffn_dim": 3584,
66
+ "encoder_layers": 18,
67
+ "encoder_no_repeat_ngram_size": 0,
68
+ "eos_token_id": null,
69
+ "exponential_decay_length_penalty": null,
70
+ "finetuning_task": null,
71
+ "forced_bos_token_id": null,
72
+ "forced_eos_token_id": null,
73
+ "id2label": {
74
+ "0": "LABEL_0",
75
+ "1": "LABEL_1"
76
+ },
77
+ "initializer_range": 0.02,
78
+ "is_decoder": false,
79
+ "is_encoder_decoder": false,
80
+ "label2id": {
81
+ "LABEL_0": 0,
82
+ "LABEL_1": 1
83
+ },
84
+ "length_penalty": 1.0,
85
+ "max_length": 20,
86
+ "max_source_positions": 1500,
87
+ "min_length": 0,
88
+ "model_type": "qwen3_asr_audio_encoder",
89
+ "n_window": 50,
90
+ "n_window_infer": 800,
91
+ "no_repeat_ngram_size": 0,
92
+ "num_beam_groups": 1,
93
+ "num_beams": 1,
94
+ "num_hidden_layers": 18,
95
+ "num_mel_bins": 128,
96
+ "num_return_sequences": 1,
97
+ "output_attentions": false,
98
+ "output_dim": 1024,
99
+ "output_hidden_states": false,
100
+ "output_scores": false,
101
+ "pad_token_id": null,
102
+ "prefix": null,
103
+ "problem_type": null,
104
+ "pruned_heads": {},
105
+ "remove_invalid_values": false,
106
+ "repetition_penalty": 1.0,
107
+ "return_dict": true,
108
+ "return_dict_in_generate": false,
109
+ "scale_embedding": false,
110
+ "sep_token_id": null,
111
+ "suppress_tokens": null,
112
+ "task_specific_params": null,
113
+ "temperature": 1.0,
114
+ "tf_legacy_loss": false,
115
+ "tie_encoder_decoder": false,
116
+ "tie_word_embeddings": true,
117
+ "tokenizer_class": null,
118
+ "top_k": 50,
119
+ "top_p": 1.0,
120
+ "torchscript": false,
121
+ "typical_p": 1.0,
122
+ "use_bfloat16": false
123
+ },
124
+ "audio_end_token_id": 151670,
125
+ "audio_start_token_id": 151669,
126
+ "audio_token_id": 151676,
127
+ "dtype": "bfloat16",
128
+ "initializer_range": 0.02,
129
+ "text_config": {
130
+ "_name_or_path": "",
131
+ "add_cross_attention": false,
132
+ "architectures": null,
133
+ "attention_bias": false,
134
+ "attention_dropout": 0.0,
135
+ "bad_words_ids": null,
136
+ "begin_suppress_tokens": null,
137
+ "bos_token_id": null,
138
+ "chunk_size_feed_forward": 0,
139
+ "cross_attention_hidden_size": null,
140
+ "decoder_start_token_id": null,
141
+ "diversity_penalty": 0.0,
142
+ "do_sample": false,
143
+ "dtype": null,
144
+ "early_stopping": false,
145
+ "encoder_no_repeat_ngram_size": 0,
146
+ "eos_token_id": null,
147
+ "exponential_decay_length_penalty": null,
148
+ "finetuning_task": null,
149
+ "forced_bos_token_id": null,
150
+ "forced_eos_token_id": null,
151
+ "head_dim": 128,
152
+ "hidden_act": "silu",
153
+ "hidden_size": 1024,
154
+ "id2label": {
155
+ "0": "LABEL_0",
156
+ "1": "LABEL_1"
157
+ },
158
+ "initializer_range": 0.02,
159
+ "intermediate_size": 3072,
160
+ "is_decoder": false,
161
+ "is_encoder_decoder": false,
162
+ "label2id": {
163
+ "LABEL_0": 0,
164
+ "LABEL_1": 1
165
+ },
166
+ "length_penalty": 1.0,
167
+ "max_length": 20,
168
+ "max_position_embeddings": 65536,
169
+ "min_length": 0,
170
+ "model_type": "qwen3",
171
+ "no_repeat_ngram_size": 0,
172
+ "num_attention_heads": 16,
173
+ "num_beam_groups": 1,
174
+ "num_beams": 1,
175
+ "num_hidden_layers": 28,
176
+ "num_key_value_heads": 8,
177
+ "num_return_sequences": 1,
178
+ "output_attentions": false,
179
+ "output_hidden_states": false,
180
+ "output_scores": false,
181
+ "pad_token_id": null,
182
+ "prefix": null,
183
+ "problem_type": null,
184
+ "pruned_heads": {},
185
+ "remove_invalid_values": false,
186
+ "repetition_penalty": 1.0,
187
+ "return_dict": true,
188
+ "return_dict_in_generate": false,
189
+ "rms_norm_eps": 1e-06,
190
+ "rope_scaling": {
191
+ "interleaved": true,
192
+ "mrope_interleaved": true,
193
+ "mrope_section": [
194
+ 24,
195
+ 20,
196
+ 20
197
+ ],
198
+ "rope_type": "default",
199
+ "type": "default"
200
+ },
201
+ "rope_theta": 1000000,
202
+ "sep_token_id": null,
203
+ "suppress_tokens": null,
204
+ "task_specific_params": null,
205
+ "temperature": 1.0,
206
+ "tf_legacy_loss": false,
207
+ "tie_encoder_decoder": false,
208
+ "tie_word_embeddings": true,
209
+ "tokenizer_class": null,
210
+ "top_k": 50,
211
+ "top_p": 1.0,
212
+ "torchscript": false,
213
+ "typical_p": 1.0,
214
+ "use_bfloat16": false,
215
+ "use_cache": true,
216
+ "vocab_size": 151936
217
+ }
218
+ },
219
+ "transformers_version": "4.57.6"
220
+ }
221
+
models/Qwen3-ASR-0.6B/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [151643,151645],
4
+ "pad_token_id": 151643,
5
+ "do_sample": false,
6
+ "temperature": 0.000001
7
+ }
models/Qwen3-ASR-0.6B/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/Qwen3-ASR-0.6B/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d6cbd4c98c7bbffe9db2edac07f56cd6637d0d5944b27f6c2b8353840323ea
3
+ size 1876091704
models/Qwen3-ASR-0.6B/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "processor_class": "Qwen3ASRProcessor",
13
+ "return_attention_mask": true
14
+ }
models/Qwen3-ASR-0.6B/tokenizer_config.json ADDED
@@ -0,0 +1,549 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<non_speech>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "151676": {
270
+ "content": "<|audio_pad|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<blank1>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<blank2>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<blank3>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<blank4>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<blank5>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<blank6>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<blank7>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<blank8>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<blank9>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<blank10>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<blank11>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<blank12>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<blank13>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<blank14>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<blank15>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<blank16>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<blank17>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<blank18>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<blank19>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<blank20>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<blank21>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<blank22>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<blank23>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<blank24>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<blank25>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<blank26>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<blank27>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<asr_text>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ }
501
+ },
502
+ "additional_special_tokens": [
503
+ "<|im_start|>",
504
+ "<|im_end|>",
505
+ "<|object_ref_start|>",
506
+ "<|object_ref_end|>",
507
+ "<|box_start|>",
508
+ "<|box_end|>",
509
+ "<|quad_start|>",
510
+ "<|quad_end|>",
511
+ "<|vision_start|>",
512
+ "<|vision_end|>",
513
+ "<|vision_pad|>",
514
+ "<|image_pad|>",
515
+ "<|video_pad|>",
516
+ "<|audio_start|>",
517
+ "<|audio_end|>",
518
+ "<tts_pad>",
519
+ "<tts_text_bos>",
520
+ "<tts_text_bos_single>",
521
+ "<|audio_pad|>"
522
+ ],
523
+ "audio_bos_token": "<|audio_start|>",
524
+ "audio_eos_token": "<|audio_end|>",
525
+ "audio_token": "<|audio_pad|>",
526
+ "bos_token": null,
527
+ "clean_up_tokenization_spaces": false,
528
+ "eos_token": "<|im_end|>",
529
+ "errors": "replace",
530
+ "extra_special_tokens": {
531
+ "audio_bos_token": "<|audio_start|>",
532
+ "audio_eos_token": "<|audio_end|>",
533
+ "audio_token": "<|audio_pad|>",
534
+ "image_token": "<|image_pad|>",
535
+ "video_token": "<|video_pad|>",
536
+ "vision_bos_token": "<|vision_start|>",
537
+ "vision_eos_token": "<|vision_end|>"
538
+ },
539
+ "image_token": "<|image_pad|>",
540
+ "model_max_length": 131072,
541
+ "pad_token": "<|endoftext|>",
542
+ "processor_class": "Qwen3ASRProcessor",
543
+ "split_special_tokens": false,
544
+ "tokenizer_class": "Qwen2Tokenizer",
545
+ "unk_token": null,
546
+ "video_token": "<|video_pad|>",
547
+ "vision_bos_token": "<|vision_start|>",
548
+ "vision_eos_token": "<|vision_end|>"
549
+ }
models/Qwen3-ASR-0.6B/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
models/fishaudioS2/s2-pro/.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ overview.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
models/fishaudioS2/s2-pro/LICENSE.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # FISH AUDIO RESEARCH LICENSE AGREEMENT
2
+
3
+ **Last Updated: March 7, 2026**
4
+
5
+ ## I. INTRODUCTION
6
+
7
+ This Agreement applies to any individual person or entity ("You", "Your" or "Licensee") that uses or distributes any portion or element of the Fish Audio Materials or Derivative Works thereof for any Research, Non-Commercial, or Commercial purpose. Capitalized terms not otherwise defined herein are defined in Section V below.
8
+
9
+ This Agreement is intended to allow research and non-commercial uses of the Materials free of charge. Any Commercial use of the Materials requires a separate license from Fish Audio.
10
+
11
+ By clicking "I Accept" or by using, distributing, or accessing any portion or element of the Fish Audio Materials or Derivative Works, You agree that You have read, understood and are bound by the terms of this Agreement. If You are acting on behalf of a company, organization or other entity, then "You" includes you and that entity, and You agree that You: (i) are an authorized representative of such entity with the authority to bind such entity to this Agreement, and (ii) You agree to the terms of this Agreement on that entity's behalf.
12
+
13
+ ## II. RESEARCH & NON-COMMERCIAL USE LICENSE
14
+
15
+ Subject to the terms of this Agreement, Fish Audio grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Fish Audio's intellectual property or other rights owned by Fish Audio embodied in the Fish Audio Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Fish Audio Materials for any Research or Non-Commercial Purpose.
16
+
17
+ "Research Purpose" means academic or scientific advancement, and in each case, is not primarily intended for commercial advantage or monetary compensation to You or others.
18
+
19
+ "Non-Commercial Purpose" means any purpose other than a Research Purpose that is not primarily intended for commercial advantage or monetary compensation to You or others, such as personal use (i.e., hobbyist) or evaluation and testing.
20
+
21
+ ## III. COMMERCIAL USE
22
+
23
+ **Any use of the Fish Audio Materials or Derivative Works for a Commercial Purpose requires a separate written license agreement from Fish Audio.** No commercial rights are granted under this Agreement.
24
+
25
+ "Commercial Purpose" means any purpose other than a Research Purpose or Non-Commercial Purpose that is primarily intended for or directed toward commercial advantage or monetary compensation to You or others, including but not limited to: (i) creating, modifying, or distributing Your product or service, including via a hosted service or application programming interface, (ii) Your business's or organization's internal operations, and (iii) any use in connection with a product or service for which You charge a fee or generate revenue, whether directly or indirectly.
26
+
27
+ To obtain a commercial license, please contact Fish Audio at:
28
+
29
+ - **Website:** [https://fish.audio](https://fish.audio)
30
+ - **Email:** business@fish.audio
31
+
32
+ ## IV. GENERAL TERMS
33
+
34
+ Your Research and Non-Commercial License under this Agreement is subject to the following terms.
35
+
36
+ ### a. Distribution & Attribution
37
+
38
+ If You distribute or make available the Fish Audio Materials or a Derivative Work to a third party, or a product or service that uses any portion of them, You shall: (i) provide a copy of this Agreement to that third party, (ii) retain the following attribution notice within a "Notice" text file distributed as a part of such copies: "This model is licensed under the Fish Audio Research License, Copyright © 39 AI, INC. All Rights Reserved.", and (iii) prominently display "Built with Fish Audio" on a related website, user interface, blogpost, about page, or product documentation.
39
+
40
+ If You create a Derivative Work, You may add your own attribution notice(s) to the "Notice" text file included with that Derivative Work, provided that You clearly indicate which attributions apply to the Fish Audio Materials and state in the "Notice" text file that You changed the Fish Audio Materials and how it was modified.
41
+
42
+ ### b. Use Restrictions
43
+
44
+ Your use of the Fish Audio Materials and Derivative Works, including any output or results of the Fish Audio Materials or Derivative Works, must comply with applicable laws and regulations (including Trade Control Laws and equivalent regulations) and adhere to Fish Audio's Acceptable Use Policy, which is hereby incorporated by reference.
45
+
46
+ Furthermore, You will not use the Fish Audio Materials or Derivative Works, or any output or results of the Fish Audio Materials or Derivative Works, to create or improve any foundational generative AI model (excluding the Models or Derivative Works).
47
+
48
+ ### c. Intellectual Property
49
+
50
+ **(i) Trademark License.** No trademark licenses are granted under this Agreement, and in connection with the Fish Audio Materials or Derivative Works, You may not use any name or mark owned by or associated with Fish Audio or any of its Affiliates, except as required under Section IV(a) herein.
51
+
52
+ **(ii) Ownership of Derivative Works.** As between You and Fish Audio, You are the owner of Derivative Works You create, subject to Fish Audio's ownership of the Fish Audio Materials and any Derivative Works made by or for Fish Audio.
53
+
54
+ **(iii) Ownership of Outputs.** As between You and Fish Audio, You own any outputs generated from the Models or Derivative Works to the extent permitted by applicable law.
55
+
56
+ **(iv) Disputes.** If You or Your Affiliate(s) institute litigation or other proceedings against Fish Audio (including a cross-claim or counterclaim in a lawsuit) alleging that the Fish Audio Materials, Derivative Works or associated outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Fish Audio from and against any claim by any third party arising out of or related to Your use or distribution of the Fish Audio Materials or Derivative Works in violation of this Agreement.
57
+
58
+ **(v) Feedback.** From time to time, You may provide Fish Audio with verbal and/or written suggestions, comments or other feedback related to Fish Audio's existing or prospective technology, products or services (collectively, "Feedback"). You are not obligated to provide Fish Audio with Feedback, but to the extent that You do, You hereby grant Fish Audio a perpetual, irrevocable, royalty-free, fully-paid, sub-licensable, transferable, non-exclusive, worldwide right and license to exploit the Feedback in any manner without restriction. Your Feedback is provided "AS IS" and You make no warranties whatsoever about any Feedback.
59
+
60
+ ### d. Disclaimer of Warranty
61
+
62
+ UNLESS REQUIRED BY APPLICABLE LAW, THE FISH AUDIO MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OR LAWFULNESS OF USING OR REDISTRIBUTING THE FISH AUDIO MATERIALS, DERIVATIVE WORKS OR ANY OUTPUT OR RESULTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE FISH AUDIO MATERIALS, DERIVATIVE WORKS AND ANY OUTPUT AND RESULTS.
63
+
64
+ ### e. Limitation of Liability
65
+
66
+ IN NO EVENT WILL FISH AUDIO OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF FISH AUDIO OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
67
+
68
+ ### f. Term and Termination
69
+
70
+ The term of this Agreement will commence upon Your acceptance of this Agreement or access to the Fish Audio Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Fish Audio may terminate this Agreement if You are in breach of any term or condition of this Agreement. Upon termination of this Agreement, You shall delete and cease use of any Fish Audio Materials or Derivative Works. Sections IV(d), (e), and (g) shall survive the termination of this Agreement.
71
+
72
+ ### g. Governing Law
73
+
74
+ This Agreement will be governed by and construed in accordance with the laws of the United States and the State of California without regard to choice of law principles, and the UN Convention on Contracts for International Sale of Goods does not apply to this Agreement.
75
+
76
+ ## V. DEFINITIONS
77
+
78
+ **"Affiliate(s)"** means any entity that directly or indirectly controls, is controlled by, or is under common control with the subject entity; for purposes of this definition, "control" means direct or indirect ownership or control of more than 50% of the voting interests of the subject entity.
79
+
80
+ **"Agreement"** means this Fish Audio Research License Agreement.
81
+
82
+ **"Derivative Work(s)"** means (a) any derivative work of the Fish Audio Materials as recognized by U.S. copyright laws and (b) any modifications to a Model, and any other model created which is based on or derived from the Model or the Model's output, including "fine tune" and "low-rank adaptation" models derived from a Model or a Model's output, but do not include the output of any Model.
83
+
84
+ **"Documentation"** means any specifications, manuals, documentation, and other written information provided by Fish Audio related to the Software or Models.
85
+
86
+ **"Fish Audio"** or **"we"** means 39 AI, INC. and its Affiliates.
87
+
88
+ **"Model(s)"** means, collectively, Fish Audio's proprietary models and algorithms, including machine-learning models, trained model weights and other elements of the foregoing.
89
+
90
+ **"Software"** means Fish Audio's proprietary software made available under this Agreement now or in the future.
91
+
92
+ **"Fish Audio Materials"** means, collectively, Fish Audio's proprietary Models, Software and Documentation (and any portion or combination thereof) made available under this Agreement.
93
+
94
+ **"Trade Control Laws"** means any applicable U.S. and non-U.S. export control and trade sanctions laws and regulations.
models/fishaudioS2/s2-pro/README.md ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - zh
4
+ - en
5
+ - ja
6
+ - ko
7
+ - es
8
+ - pt
9
+ - ar
10
+ - ru
11
+ - fr
12
+ - de
13
+ - sv
14
+ - it
15
+ - tr
16
+ - 'no'
17
+ - nl
18
+ - cy
19
+ - eu
20
+ - ca
21
+ - da
22
+ - gl
23
+ - ta
24
+ - hu
25
+ - fi
26
+ - pl
27
+ - et
28
+ - hi
29
+ - la
30
+ - ur
31
+ - th
32
+ - vi
33
+ - jw
34
+ - bn
35
+ - yo
36
+ - sl
37
+ - cs
38
+ - sw
39
+ - nn
40
+ - he
41
+ - ms
42
+ - uk
43
+ - id
44
+ - kk
45
+ - bg
46
+ - lv
47
+ - my
48
+ - tl
49
+ - sk
50
+ - ne
51
+ - fa
52
+ - af
53
+ - el
54
+ - bo
55
+ - hr
56
+ - ro
57
+ - sn
58
+ - mi
59
+ - yi
60
+ - am
61
+ - be
62
+ - km
63
+ - is
64
+ - az
65
+ - sd
66
+ - br
67
+ - sq
68
+ - ps
69
+ - mn
70
+ - ht
71
+ - ml
72
+ - sr
73
+ - sa
74
+ - te
75
+ - ka
76
+ - bs
77
+ - pa
78
+ - lt
79
+ - kn
80
+ - si
81
+ - hy
82
+ - mr
83
+ - as
84
+ - gu
85
+ - fo
86
+ license: other
87
+ license_name: fish-audio-research-license
88
+ license_link: LICENSE.md
89
+ pipeline_tag: text-to-speech
90
+ tags:
91
+ - text-to-speech
92
+ - instruction-following
93
+ - multilingual
94
+ inference: false
95
+ extra_gated_prompt: You agree to not use the model to generate contents that violate
96
+ DMCA or local laws.
97
+ extra_gated_fields:
98
+ Country: country
99
+ Specific date: date_picker
100
+ I agree to use this model for non-commercial use ONLY: checkbox
101
+ ---
102
+
103
+ # Fish Audio S2 Pro
104
+
105
+ <img src="overview.png" alt="Fish Audio S2 Pro overview — fine-grained control, multi-speaker multi-turn generation, low-latency streaming, and long-context inference." width="100%">
106
+
107
+ [**Technical Report**](https://huggingface.co/papers/2603.08823) | [**GitHub**](https://github.com/fishaudio/fish-speech) | [**Playground**](https://fish.audio)
108
+
109
+ **Fish Audio S2 Pro** is a leading text-to-speech (TTS) model with fine-grained inline control of prosody and emotion. Trained on over 10M+ hours of audio data across 80+ languages, the system combines reinforcement learning alignment with a dual-autoregressive architecture. The release includes model weights, fine-tuning code, and an SGLang-based streaming inference engine.
110
+
111
+ ## Architecture
112
+
113
+ S2 Pro builds on a decoder-only transformer combined with an RVQ-based audio codec (10 codebooks, ~21 Hz frame rate) using a **Dual-Autoregressive (Dual-AR)** architecture:
114
+
115
+ - **Slow AR** (4B parameters): Operates along the time axis and predicts the primary semantic codebook.
116
+ - **Fast AR** (400M parameters): Generates the remaining 9 residual codebooks at each time step, reconstructing fine-grained acoustic detail.
117
+
118
+ This asymmetric design keeps inference efficient while preserving audio fidelity. Because the Dual-AR architecture is structurally isomorphic to standard autoregressive LLMs, it inherits all LLM-native serving optimizations from SGLang — including continuous batching, paged KV cache, CUDA graph replay, and RadixAttention-based prefix caching.
119
+
120
+ ## Fine-Grained Inline Control
121
+
122
+ S2 Pro enables localized control over speech generation by embedding natural-language instructions directly within the text using `[tag]` syntax. Rather than relying on a fixed set of predefined tags, S2 Pro accepts **free-form textual descriptions** — such as `[whisper in small voice]`, `[professional broadcast tone]`, or `[pitch up]` — allowing open-ended expression control at the word level.
123
+
124
+ **Common tags (15,000+ unique tags supported):**
125
+
126
+ `[pause]` `[emphasis]` `[laughing]` `[inhale]` `[chuckle]` `[tsk]` `[singing]` `[excited]` `[laughing tone]` `[interrupting]` `[chuckling]` `[excited tone]` `[volume up]` `[echo]` `[angry]` `[low volume]` `[sigh]` `[low voice]` `[whisper]` `[screaming]` `[shouting]` `[loud]` `[surprised]` `[short pause]` `[exhale]` `[delight]` `[panting]` `[audience laughter]` `[with strong accent]` `[volume down]` `[clearing throat]` `[sad]` `[moaning]` `[shocked]`
127
+
128
+ ## Supported Languages
129
+
130
+ S2 Pro supports 80+ languages.
131
+
132
+ **Tier 1:** Japanese (ja), English (en), Chinese (zh)
133
+
134
+ **Tier 2:** Korean (ko), Spanish (es), Portuguese (pt), Arabic (ar), Russian (ru), French (fr), German (de)
135
+
136
+ **Other supported languages:** sv, it, tr, no, nl, cy, eu, ca, da, gl, ta, hu, fi, pl, et, hi, la, ur, th, vi, jw, bn, yo, xsl, cs, sw, nn, he, ms, uk, id, kk, bg, lv, my, tl, sk, ne, fa, af, el, bo, hr, ro, sn, mi, yi, am, be, km, is, az, sd, br, sq, ps, mn, ht, ml, sr, sa, te, ka, bs, pa, lt, kn, si, hy, mr, as, gu, fo, and more.
137
+
138
+ ## Production Streaming Performance
139
+
140
+ On a single NVIDIA H200 GPU:
141
+
142
+ - **Real-Time Factor (RTF):** 0.195
143
+ - **Time-to-first-audio:** ~100 ms
144
+ - **Throughput:** 3,000+ acoustic tokens/s while maintaining RTF below 0.5
145
+
146
+ ## Links
147
+
148
+ - [Fish Speech GitHub](https://github.com/fishaudio/fish-speech)
149
+ - [Fish Audio Playground](https://fish.audio)
150
+ - [Blog & Tech Report](https://fish.audio/blog/fish-audio-open-sources-s2/)
151
+
152
+ ## Technical Report
153
+
154
+ If you find our work useful, please consider citing our report:
155
+
156
+ ```bibtex
157
+ @misc{liao2026fishaudios2technical,
158
+ title={Fish Audio S2 Technical Report},
159
+ author={Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han},
160
+ year={2026},
161
+ eprint={2603.08823},
162
+ archivePrefix={arXiv},
163
+ primaryClass={cs.SD},
164
+ url={https://arxiv.org/abs/2603.08823},
165
+ }
166
+ ```
167
+
168
+ ## License
169
+
170
+ This model is licensed under the [Fish Audio Research License](LICENSE.md). Research and non-commercial use is permitted free of charge. Commercial use requires a separate license from Fish Audio — contact business@fish.audio.
models/fishaudioS2/s2-pro/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
models/fishaudioS2/s2-pro/codec.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fc41c5a7151c6f350af8bd7e5d6e3accfcc7f3dfbfac23afd35af07052bb2f
3
+ size 1871099728
models/fishaudioS2/s2-pro/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_decoder_config": {
3
+ "attention_o_bias": false,
4
+ "attention_qk_norm": false,
5
+ "attention_qkv_bias": false,
6
+ "audio_hidden_dim": 5120,
7
+ "dim": 2560,
8
+ "dropout": 0.0,
9
+ "head_dim": 128,
10
+ "initializer_range": 0.01976423537605237,
11
+ "intermediate_size": 9728,
12
+ "max_seq_len": 11,
13
+ "model_type": "fish_qwen3_audio_decoder",
14
+ "moe_intermediate_size": 768,
15
+ "n_head": 32,
16
+ "n_layer": 4,
17
+ "n_local_heads": 8,
18
+ "norm_eps": 1e-06,
19
+ "norm_topk_prob": true,
20
+ "num_codebooks": 10,
21
+ "num_experts": 1,
22
+ "num_experts_per_tok": 1,
23
+ "rope_base": 1000000,
24
+ "router_gamma": 0.001,
25
+ "text_dim": 2560,
26
+ "tie_word_embeddings": false,
27
+ "use_aux_loss_free": false,
28
+ "use_bfloat16": false,
29
+ "use_gradient_checkpointing": true,
30
+ "use_moe": false,
31
+ "vocab_size": 4096
32
+ },
33
+ "audio_pad_token_id": 151677,
34
+ "dtype": "bfloat16",
35
+ "eos_token_id": 151645,
36
+ "model_type": "fish_qwen3_omni",
37
+ "pad_token_id": 151669,
38
+ "semantic_end_token_id": 155773,
39
+ "semantic_start_token_id": 151678,
40
+ "text_config": {
41
+ "attention_o_bias": false,
42
+ "attention_qk_norm": true,
43
+ "attention_qkv_bias": false,
44
+ "audio_hidden_dim": 5120,
45
+ "dim": 2560,
46
+ "dropout": 0.0,
47
+ "head_dim": 128,
48
+ "initializer_range": 0.01976423537605237,
49
+ "intermediate_size": 9728,
50
+ "max_seq_len": 32768,
51
+ "model_type": "fish_qwen3",
52
+ "moe_intermediate_size": 768,
53
+ "n_head": 32,
54
+ "n_layer": 36,
55
+ "n_local_heads": 8,
56
+ "norm_eps": 1e-06,
57
+ "norm_topk_prob": true,
58
+ "num_experts": 1,
59
+ "num_experts_per_tok": 1,
60
+ "rope_base": 1000000,
61
+ "router_gamma": 0.001,
62
+ "tie_word_embeddings": true,
63
+ "use_aux_loss_free": false,
64
+ "use_bfloat16": false,
65
+ "use_gradient_checkpointing": true,
66
+ "use_moe": false,
67
+ "vocab_size": 155776
68
+ },
69
+ "transformers_version": "4.57.1"
70
+ }
models/fishaudioS2/s2-pro/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4218e8ac93be83b35eee30b4f94cb2e9b5ecff40f3e21611438d2f4f8804aad
3
+ size 4986872984
models/fishaudioS2/s2-pro/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76738d23465deaac431433232c0762908cc99a6eddc3d49f67307d92680827be
3
+ size 4136876104
models/fishaudioS2/s2-pro/model.safetensors.index.json ADDED
@@ -0,0 +1,366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4561852416,
4
+ "total_size": 9123704832
5
+ },
6
+ "weight_map": {
7
+ "audio_decoder.codebook_embeddings.weight": "model-00002-of-00002.safetensors",
8
+ "audio_decoder.embeddings.weight": "model-00002-of-00002.safetensors",
9
+ "audio_decoder.layers.0.attention.wo.weight": "model-00002-of-00002.safetensors",
10
+ "audio_decoder.layers.0.attention.wqkv.weight": "model-00002-of-00002.safetensors",
11
+ "audio_decoder.layers.0.attention_norm.weight": "model-00002-of-00002.safetensors",
12
+ "audio_decoder.layers.0.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
13
+ "audio_decoder.layers.0.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
14
+ "audio_decoder.layers.0.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
15
+ "audio_decoder.layers.0.ffn_norm.weight": "model-00002-of-00002.safetensors",
16
+ "audio_decoder.layers.1.attention.wo.weight": "model-00002-of-00002.safetensors",
17
+ "audio_decoder.layers.1.attention.wqkv.weight": "model-00002-of-00002.safetensors",
18
+ "audio_decoder.layers.1.attention_norm.weight": "model-00002-of-00002.safetensors",
19
+ "audio_decoder.layers.1.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
20
+ "audio_decoder.layers.1.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
21
+ "audio_decoder.layers.1.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
22
+ "audio_decoder.layers.1.ffn_norm.weight": "model-00002-of-00002.safetensors",
23
+ "audio_decoder.layers.2.attention.wo.weight": "model-00002-of-00002.safetensors",
24
+ "audio_decoder.layers.2.attention.wqkv.weight": "model-00002-of-00002.safetensors",
25
+ "audio_decoder.layers.2.attention_norm.weight": "model-00002-of-00002.safetensors",
26
+ "audio_decoder.layers.2.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
27
+ "audio_decoder.layers.2.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
28
+ "audio_decoder.layers.2.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
29
+ "audio_decoder.layers.2.ffn_norm.weight": "model-00002-of-00002.safetensors",
30
+ "audio_decoder.layers.3.attention.wo.weight": "model-00002-of-00002.safetensors",
31
+ "audio_decoder.layers.3.attention.wqkv.weight": "model-00002-of-00002.safetensors",
32
+ "audio_decoder.layers.3.attention_norm.weight": "model-00002-of-00002.safetensors",
33
+ "audio_decoder.layers.3.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
34
+ "audio_decoder.layers.3.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
35
+ "audio_decoder.layers.3.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
36
+ "audio_decoder.layers.3.ffn_norm.weight": "model-00002-of-00002.safetensors",
37
+ "audio_decoder.norm.weight": "model-00002-of-00002.safetensors",
38
+ "audio_decoder.output.weight": "model-00002-of-00002.safetensors",
39
+ "text_model.model.embeddings.weight": "model-00001-of-00002.safetensors",
40
+ "text_model.model.layers.0.attention.k_norm.weight": "model-00001-of-00002.safetensors",
41
+ "text_model.model.layers.0.attention.q_norm.weight": "model-00001-of-00002.safetensors",
42
+ "text_model.model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
43
+ "text_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
44
+ "text_model.model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
45
+ "text_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
46
+ "text_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
47
+ "text_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
48
+ "text_model.model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
49
+ "text_model.model.layers.1.attention.k_norm.weight": "model-00001-of-00002.safetensors",
50
+ "text_model.model.layers.1.attention.q_norm.weight": "model-00001-of-00002.safetensors",
51
+ "text_model.model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
52
+ "text_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
53
+ "text_model.model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
54
+ "text_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
55
+ "text_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
56
+ "text_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
57
+ "text_model.model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
58
+ "text_model.model.layers.10.attention.k_norm.weight": "model-00001-of-00002.safetensors",
59
+ "text_model.model.layers.10.attention.q_norm.weight": "model-00001-of-00002.safetensors",
60
+ "text_model.model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
61
+ "text_model.model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
62
+ "text_model.model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
63
+ "text_model.model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
64
+ "text_model.model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
65
+ "text_model.model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
66
+ "text_model.model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
67
+ "text_model.model.layers.11.attention.k_norm.weight": "model-00001-of-00002.safetensors",
68
+ "text_model.model.layers.11.attention.q_norm.weight": "model-00001-of-00002.safetensors",
69
+ "text_model.model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
70
+ "text_model.model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
71
+ "text_model.model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
72
+ "text_model.model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
73
+ "text_model.model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
74
+ "text_model.model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
75
+ "text_model.model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
76
+ "text_model.model.layers.12.attention.k_norm.weight": "model-00001-of-00002.safetensors",
77
+ "text_model.model.layers.12.attention.q_norm.weight": "model-00001-of-00002.safetensors",
78
+ "text_model.model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
79
+ "text_model.model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
80
+ "text_model.model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
81
+ "text_model.model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
82
+ "text_model.model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
83
+ "text_model.model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
84
+ "text_model.model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
85
+ "text_model.model.layers.13.attention.k_norm.weight": "model-00001-of-00002.safetensors",
86
+ "text_model.model.layers.13.attention.q_norm.weight": "model-00001-of-00002.safetensors",
87
+ "text_model.model.layers.13.attention.wo.weight": "model-00001-of-00002.safetensors",
88
+ "text_model.model.layers.13.attention.wqkv.weight": "model-00001-of-00002.safetensors",
89
+ "text_model.model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
90
+ "text_model.model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
91
+ "text_model.model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
92
+ "text_model.model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
93
+ "text_model.model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
94
+ "text_model.model.layers.14.attention.k_norm.weight": "model-00001-of-00002.safetensors",
95
+ "text_model.model.layers.14.attention.q_norm.weight": "model-00001-of-00002.safetensors",
96
+ "text_model.model.layers.14.attention.wo.weight": "model-00001-of-00002.safetensors",
97
+ "text_model.model.layers.14.attention.wqkv.weight": "model-00001-of-00002.safetensors",
98
+ "text_model.model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
99
+ "text_model.model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
100
+ "text_model.model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
101
+ "text_model.model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
102
+ "text_model.model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
103
+ "text_model.model.layers.15.attention.k_norm.weight": "model-00001-of-00002.safetensors",
104
+ "text_model.model.layers.15.attention.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "text_model.model.layers.15.attention.wo.weight": "model-00001-of-00002.safetensors",
106
+ "text_model.model.layers.15.attention.wqkv.weight": "model-00001-of-00002.safetensors",
107
+ "text_model.model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
108
+ "text_model.model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
109
+ "text_model.model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
110
+ "text_model.model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
111
+ "text_model.model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
112
+ "text_model.model.layers.16.attention.k_norm.weight": "model-00001-of-00002.safetensors",
113
+ "text_model.model.layers.16.attention.q_norm.weight": "model-00001-of-00002.safetensors",
114
+ "text_model.model.layers.16.attention.wo.weight": "model-00001-of-00002.safetensors",
115
+ "text_model.model.layers.16.attention.wqkv.weight": "model-00001-of-00002.safetensors",
116
+ "text_model.model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
117
+ "text_model.model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
118
+ "text_model.model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
119
+ "text_model.model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
120
+ "text_model.model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
121
+ "text_model.model.layers.17.attention.k_norm.weight": "model-00001-of-00002.safetensors",
122
+ "text_model.model.layers.17.attention.q_norm.weight": "model-00001-of-00002.safetensors",
123
+ "text_model.model.layers.17.attention.wo.weight": "model-00001-of-00002.safetensors",
124
+ "text_model.model.layers.17.attention.wqkv.weight": "model-00001-of-00002.safetensors",
125
+ "text_model.model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
126
+ "text_model.model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
127
+ "text_model.model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
128
+ "text_model.model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
129
+ "text_model.model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
130
+ "text_model.model.layers.18.attention.k_norm.weight": "model-00001-of-00002.safetensors",
131
+ "text_model.model.layers.18.attention.q_norm.weight": "model-00001-of-00002.safetensors",
132
+ "text_model.model.layers.18.attention.wo.weight": "model-00001-of-00002.safetensors",
133
+ "text_model.model.layers.18.attention.wqkv.weight": "model-00001-of-00002.safetensors",
134
+ "text_model.model.layers.18.attention_norm.weight": "model-00001-of-00002.safetensors",
135
+ "text_model.model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
136
+ "text_model.model.layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
137
+ "text_model.model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
138
+ "text_model.model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
139
+ "text_model.model.layers.19.attention.k_norm.weight": "model-00001-of-00002.safetensors",
140
+ "text_model.model.layers.19.attention.q_norm.weight": "model-00001-of-00002.safetensors",
141
+ "text_model.model.layers.19.attention.wo.weight": "model-00001-of-00002.safetensors",
142
+ "text_model.model.layers.19.attention.wqkv.weight": "model-00001-of-00002.safetensors",
143
+ "text_model.model.layers.19.attention_norm.weight": "model-00001-of-00002.safetensors",
144
+ "text_model.model.layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
145
+ "text_model.model.layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
146
+ "text_model.model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
147
+ "text_model.model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
148
+ "text_model.model.layers.2.attention.k_norm.weight": "model-00001-of-00002.safetensors",
149
+ "text_model.model.layers.2.attention.q_norm.weight": "model-00001-of-00002.safetensors",
150
+ "text_model.model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
151
+ "text_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
152
+ "text_model.model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
153
+ "text_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
154
+ "text_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
155
+ "text_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
156
+ "text_model.model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
157
+ "text_model.model.layers.20.attention.k_norm.weight": "model-00001-of-00002.safetensors",
158
+ "text_model.model.layers.20.attention.q_norm.weight": "model-00001-of-00002.safetensors",
159
+ "text_model.model.layers.20.attention.wo.weight": "model-00001-of-00002.safetensors",
160
+ "text_model.model.layers.20.attention.wqkv.weight": "model-00001-of-00002.safetensors",
161
+ "text_model.model.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
162
+ "text_model.model.layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
163
+ "text_model.model.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
164
+ "text_model.model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
165
+ "text_model.model.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
166
+ "text_model.model.layers.21.attention.k_norm.weight": "model-00002-of-00002.safetensors",
167
+ "text_model.model.layers.21.attention.q_norm.weight": "model-00002-of-00002.safetensors",
168
+ "text_model.model.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
169
+ "text_model.model.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
170
+ "text_model.model.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
171
+ "text_model.model.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
172
+ "text_model.model.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
173
+ "text_model.model.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
174
+ "text_model.model.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
175
+ "text_model.model.layers.22.attention.k_norm.weight": "model-00002-of-00002.safetensors",
176
+ "text_model.model.layers.22.attention.q_norm.weight": "model-00002-of-00002.safetensors",
177
+ "text_model.model.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
178
+ "text_model.model.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
179
+ "text_model.model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
180
+ "text_model.model.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
181
+ "text_model.model.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
182
+ "text_model.model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
183
+ "text_model.model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
184
+ "text_model.model.layers.23.attention.k_norm.weight": "model-00002-of-00002.safetensors",
185
+ "text_model.model.layers.23.attention.q_norm.weight": "model-00002-of-00002.safetensors",
186
+ "text_model.model.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
187
+ "text_model.model.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
188
+ "text_model.model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
189
+ "text_model.model.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
190
+ "text_model.model.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
191
+ "text_model.model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
192
+ "text_model.model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
193
+ "text_model.model.layers.24.attention.k_norm.weight": "model-00002-of-00002.safetensors",
194
+ "text_model.model.layers.24.attention.q_norm.weight": "model-00002-of-00002.safetensors",
195
+ "text_model.model.layers.24.attention.wo.weight": "model-00002-of-00002.safetensors",
196
+ "text_model.model.layers.24.attention.wqkv.weight": "model-00002-of-00002.safetensors",
197
+ "text_model.model.layers.24.attention_norm.weight": "model-00002-of-00002.safetensors",
198
+ "text_model.model.layers.24.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
199
+ "text_model.model.layers.24.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
200
+ "text_model.model.layers.24.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
201
+ "text_model.model.layers.24.ffn_norm.weight": "model-00002-of-00002.safetensors",
202
+ "text_model.model.layers.25.attention.k_norm.weight": "model-00002-of-00002.safetensors",
203
+ "text_model.model.layers.25.attention.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "text_model.model.layers.25.attention.wo.weight": "model-00002-of-00002.safetensors",
205
+ "text_model.model.layers.25.attention.wqkv.weight": "model-00002-of-00002.safetensors",
206
+ "text_model.model.layers.25.attention_norm.weight": "model-00002-of-00002.safetensors",
207
+ "text_model.model.layers.25.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
208
+ "text_model.model.layers.25.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
209
+ "text_model.model.layers.25.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
210
+ "text_model.model.layers.25.ffn_norm.weight": "model-00002-of-00002.safetensors",
211
+ "text_model.model.layers.26.attention.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "text_model.model.layers.26.attention.q_norm.weight": "model-00002-of-00002.safetensors",
213
+ "text_model.model.layers.26.attention.wo.weight": "model-00002-of-00002.safetensors",
214
+ "text_model.model.layers.26.attention.wqkv.weight": "model-00002-of-00002.safetensors",
215
+ "text_model.model.layers.26.attention_norm.weight": "model-00002-of-00002.safetensors",
216
+ "text_model.model.layers.26.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
217
+ "text_model.model.layers.26.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
218
+ "text_model.model.layers.26.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
219
+ "text_model.model.layers.26.ffn_norm.weight": "model-00002-of-00002.safetensors",
220
+ "text_model.model.layers.27.attention.k_norm.weight": "model-00002-of-00002.safetensors",
221
+ "text_model.model.layers.27.attention.q_norm.weight": "model-00002-of-00002.safetensors",
222
+ "text_model.model.layers.27.attention.wo.weight": "model-00002-of-00002.safetensors",
223
+ "text_model.model.layers.27.attention.wqkv.weight": "model-00002-of-00002.safetensors",
224
+ "text_model.model.layers.27.attention_norm.weight": "model-00002-of-00002.safetensors",
225
+ "text_model.model.layers.27.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
226
+ "text_model.model.layers.27.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
227
+ "text_model.model.layers.27.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
228
+ "text_model.model.layers.27.ffn_norm.weight": "model-00002-of-00002.safetensors",
229
+ "text_model.model.layers.28.attention.k_norm.weight": "model-00002-of-00002.safetensors",
230
+ "text_model.model.layers.28.attention.q_norm.weight": "model-00002-of-00002.safetensors",
231
+ "text_model.model.layers.28.attention.wo.weight": "model-00002-of-00002.safetensors",
232
+ "text_model.model.layers.28.attention.wqkv.weight": "model-00002-of-00002.safetensors",
233
+ "text_model.model.layers.28.attention_norm.weight": "model-00002-of-00002.safetensors",
234
+ "text_model.model.layers.28.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
235
+ "text_model.model.layers.28.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
236
+ "text_model.model.layers.28.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
237
+ "text_model.model.layers.28.ffn_norm.weight": "model-00002-of-00002.safetensors",
238
+ "text_model.model.layers.29.attention.k_norm.weight": "model-00002-of-00002.safetensors",
239
+ "text_model.model.layers.29.attention.q_norm.weight": "model-00002-of-00002.safetensors",
240
+ "text_model.model.layers.29.attention.wo.weight": "model-00002-of-00002.safetensors",
241
+ "text_model.model.layers.29.attention.wqkv.weight": "model-00002-of-00002.safetensors",
242
+ "text_model.model.layers.29.attention_norm.weight": "model-00002-of-00002.safetensors",
243
+ "text_model.model.layers.29.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
244
+ "text_model.model.layers.29.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
245
+ "text_model.model.layers.29.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
246
+ "text_model.model.layers.29.ffn_norm.weight": "model-00002-of-00002.safetensors",
247
+ "text_model.model.layers.3.attention.k_norm.weight": "model-00001-of-00002.safetensors",
248
+ "text_model.model.layers.3.attention.q_norm.weight": "model-00001-of-00002.safetensors",
249
+ "text_model.model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
250
+ "text_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
251
+ "text_model.model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
252
+ "text_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
253
+ "text_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
254
+ "text_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
255
+ "text_model.model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
256
+ "text_model.model.layers.30.attention.k_norm.weight": "model-00002-of-00002.safetensors",
257
+ "text_model.model.layers.30.attention.q_norm.weight": "model-00002-of-00002.safetensors",
258
+ "text_model.model.layers.30.attention.wo.weight": "model-00002-of-00002.safetensors",
259
+ "text_model.model.layers.30.attention.wqkv.weight": "model-00002-of-00002.safetensors",
260
+ "text_model.model.layers.30.attention_norm.weight": "model-00002-of-00002.safetensors",
261
+ "text_model.model.layers.30.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
262
+ "text_model.model.layers.30.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
263
+ "text_model.model.layers.30.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
264
+ "text_model.model.layers.30.ffn_norm.weight": "model-00002-of-00002.safetensors",
265
+ "text_model.model.layers.31.attention.k_norm.weight": "model-00002-of-00002.safetensors",
266
+ "text_model.model.layers.31.attention.q_norm.weight": "model-00002-of-00002.safetensors",
267
+ "text_model.model.layers.31.attention.wo.weight": "model-00002-of-00002.safetensors",
268
+ "text_model.model.layers.31.attention.wqkv.weight": "model-00002-of-00002.safetensors",
269
+ "text_model.model.layers.31.attention_norm.weight": "model-00002-of-00002.safetensors",
270
+ "text_model.model.layers.31.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
271
+ "text_model.model.layers.31.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
272
+ "text_model.model.layers.31.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
273
+ "text_model.model.layers.31.ffn_norm.weight": "model-00002-of-00002.safetensors",
274
+ "text_model.model.layers.32.attention.k_norm.weight": "model-00002-of-00002.safetensors",
275
+ "text_model.model.layers.32.attention.q_norm.weight": "model-00002-of-00002.safetensors",
276
+ "text_model.model.layers.32.attention.wo.weight": "model-00002-of-00002.safetensors",
277
+ "text_model.model.layers.32.attention.wqkv.weight": "model-00002-of-00002.safetensors",
278
+ "text_model.model.layers.32.attention_norm.weight": "model-00002-of-00002.safetensors",
279
+ "text_model.model.layers.32.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
280
+ "text_model.model.layers.32.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
281
+ "text_model.model.layers.32.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
282
+ "text_model.model.layers.32.ffn_norm.weight": "model-00002-of-00002.safetensors",
283
+ "text_model.model.layers.33.attention.k_norm.weight": "model-00002-of-00002.safetensors",
284
+ "text_model.model.layers.33.attention.q_norm.weight": "model-00002-of-00002.safetensors",
285
+ "text_model.model.layers.33.attention.wo.weight": "model-00002-of-00002.safetensors",
286
+ "text_model.model.layers.33.attention.wqkv.weight": "model-00002-of-00002.safetensors",
287
+ "text_model.model.layers.33.attention_norm.weight": "model-00002-of-00002.safetensors",
288
+ "text_model.model.layers.33.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
289
+ "text_model.model.layers.33.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
290
+ "text_model.model.layers.33.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
291
+ "text_model.model.layers.33.ffn_norm.weight": "model-00002-of-00002.safetensors",
292
+ "text_model.model.layers.34.attention.k_norm.weight": "model-00002-of-00002.safetensors",
293
+ "text_model.model.layers.34.attention.q_norm.weight": "model-00002-of-00002.safetensors",
294
+ "text_model.model.layers.34.attention.wo.weight": "model-00002-of-00002.safetensors",
295
+ "text_model.model.layers.34.attention.wqkv.weight": "model-00002-of-00002.safetensors",
296
+ "text_model.model.layers.34.attention_norm.weight": "model-00002-of-00002.safetensors",
297
+ "text_model.model.layers.34.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
298
+ "text_model.model.layers.34.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
299
+ "text_model.model.layers.34.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
300
+ "text_model.model.layers.34.ffn_norm.weight": "model-00002-of-00002.safetensors",
301
+ "text_model.model.layers.35.attention.k_norm.weight": "model-00002-of-00002.safetensors",
302
+ "text_model.model.layers.35.attention.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "text_model.model.layers.35.attention.wo.weight": "model-00002-of-00002.safetensors",
304
+ "text_model.model.layers.35.attention.wqkv.weight": "model-00002-of-00002.safetensors",
305
+ "text_model.model.layers.35.attention_norm.weight": "model-00002-of-00002.safetensors",
306
+ "text_model.model.layers.35.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
307
+ "text_model.model.layers.35.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
308
+ "text_model.model.layers.35.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
309
+ "text_model.model.layers.35.ffn_norm.weight": "model-00002-of-00002.safetensors",
310
+ "text_model.model.layers.4.attention.k_norm.weight": "model-00001-of-00002.safetensors",
311
+ "text_model.model.layers.4.attention.q_norm.weight": "model-00001-of-00002.safetensors",
312
+ "text_model.model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
313
+ "text_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
314
+ "text_model.model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
315
+ "text_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
316
+ "text_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
317
+ "text_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
318
+ "text_model.model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
319
+ "text_model.model.layers.5.attention.k_norm.weight": "model-00001-of-00002.safetensors",
320
+ "text_model.model.layers.5.attention.q_norm.weight": "model-00001-of-00002.safetensors",
321
+ "text_model.model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
322
+ "text_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
323
+ "text_model.model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
324
+ "text_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
325
+ "text_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
326
+ "text_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
327
+ "text_model.model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
328
+ "text_model.model.layers.6.attention.k_norm.weight": "model-00001-of-00002.safetensors",
329
+ "text_model.model.layers.6.attention.q_norm.weight": "model-00001-of-00002.safetensors",
330
+ "text_model.model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
331
+ "text_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
332
+ "text_model.model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
333
+ "text_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
334
+ "text_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
335
+ "text_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
336
+ "text_model.model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
337
+ "text_model.model.layers.7.attention.k_norm.weight": "model-00001-of-00002.safetensors",
338
+ "text_model.model.layers.7.attention.q_norm.weight": "model-00001-of-00002.safetensors",
339
+ "text_model.model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
340
+ "text_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
341
+ "text_model.model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
342
+ "text_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
343
+ "text_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
344
+ "text_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
345
+ "text_model.model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
346
+ "text_model.model.layers.8.attention.k_norm.weight": "model-00001-of-00002.safetensors",
347
+ "text_model.model.layers.8.attention.q_norm.weight": "model-00001-of-00002.safetensors",
348
+ "text_model.model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
349
+ "text_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
350
+ "text_model.model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
351
+ "text_model.model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
352
+ "text_model.model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
353
+ "text_model.model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
354
+ "text_model.model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
355
+ "text_model.model.layers.9.attention.k_norm.weight": "model-00001-of-00002.safetensors",
356
+ "text_model.model.layers.9.attention.q_norm.weight": "model-00001-of-00002.safetensors",
357
+ "text_model.model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
358
+ "text_model.model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
359
+ "text_model.model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
360
+ "text_model.model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
361
+ "text_model.model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
362
+ "text_model.model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
363
+ "text_model.model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
364
+ "text_model.model.norm.weight": "model-00002-of-00002.safetensors"
365
+ }
366
+ }
models/fishaudioS2/s2-pro/overview.png ADDED

Git LFS Details

  • SHA256: f77da18e7d3cf59182fb714fc6c1bc526e7877b538e6380d8f002e84e8c56ea9
  • Pointer size: 132 Bytes
  • Size of remote file: 3.54 MB
models/fishaudioS2/s2-pro/special_tokens_map.json ADDED
The diff for this file is too large to render. See raw diff
 
models/fishaudioS2/s2-pro/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24e08099d45a8adf3f52f5f0b03276e433bb9d689bb15fcbcc48ce58744588b
3
+ size 12217872
models/fishaudioS2/s2-pro/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
voice-preprocessing-lock.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "asr": {
3
+ "forced_aligner": false,
4
+ "repository": "Qwen/Qwen3-ASR-0.6B",
5
+ "revision": "5eb144179a02acc5e5ba31e748d22b0cf3e303b0",
6
+ "weight_bytes": 1876091704,
7
+ "weight_file": "model.safetensors",
8
+ "weight_sha256": "79d6cbd4c98c7bbffe9db2edac07f56cd6637d0d5944b27f6c2b8353840323ea"
9
+ },
10
+ "contract_version": "h3-voice-preprocessing-v1",
11
+ "fish": {
12
+ "large_files": [
13
+ {
14
+ "bytes": 1871099728,
15
+ "path": "codec.pth",
16
+ "sha256": "74fc41c5a7151c6f350af8bd7e5d6e3accfcc7f3dfbfac23afd35af07052bb2f"
17
+ },
18
+ {
19
+ "bytes": 4986872984,
20
+ "path": "model-00001-of-00002.safetensors",
21
+ "sha256": "c4218e8ac93be83b35eee30b4f94cb2e9b5ecff40f3e21611438d2f4f8804aad"
22
+ },
23
+ {
24
+ "bytes": 4136876104,
25
+ "path": "model-00002-of-00002.safetensors",
26
+ "sha256": "76738d23465deaac431433232c0762908cc99a6eddc3d49f67307d92680827be"
27
+ }
28
+ ],
29
+ "model_option": "s2-pro-bnb-nf4",
30
+ "model_repository": "fishaudio/s2-pro",
31
+ "model_revision": "1de9996b6be38b745688de084d87a5633f714e4e",
32
+ "node_repository": "https://github.com/Saganaki22/ComfyUI-FishAudioS2.git",
33
+ "node_revision": "521f33fe79c081da314dc905ce399c62edb24749",
34
+ "quantization": "bitsandbytes NF4 applied at load time",
35
+ "workflow": "workflows/fish_s2_reference.api.json",
36
+ "workflow_sha256": "9af5b686f4a3d0c8d29759ab7783cf4cba0aa726387596e2213bf771ed62c2dc"
37
+ },
38
+ "normalization": {
39
+ "buckets": [
40
+ {
41
+ "h3_target_frames": 73,
42
+ "name": "short",
43
+ "seconds": 3.072,
44
+ "waveform_frames": 98304
45
+ },
46
+ {
47
+ "h3_target_frames": 124,
48
+ "name": "long",
49
+ "seconds": 5.184,
50
+ "waveform_frames": 165888
51
+ }
52
+ ],
53
+ "format": "stereo PCM16 WAV",
54
+ "regenerate_oversized_clips": false,
55
+ "sample_rate": 32000,
56
+ "selection": "Use the shortest bucket that contains the clip after silence trimming. Pad shorter clips and truncate clips longer than the long bucket.",
57
+ "trim_leading_and_trailing_silence": true
58
+ },
59
+ "prompt_set": {
60
+ "clip_count": 10,
61
+ "default_language": "en",
62
+ "path": "prompts/audio_dataset.v1.json",
63
+ "sha256": "e612f5ab9922198bd6634402e51198272d8b15f54b3b7061b7dbc1961fc586f5",
64
+ "supported_languages": [
65
+ "en",
66
+ "ko",
67
+ "ja",
68
+ "zh"
69
+ ],
70
+ "version": "audio-dataset-v1"
71
+ },
72
+ "seed_policy": "Use the first 31 bits of SHA-256(train_id) as a base and add the zero-based script index modulo 2^31, yielding ten deterministic distinct seeds."
73
+ }