Text-to-Speech
Transformers
Safetensors
moss_tts_realtime
feature-extraction
audio
moss-tts
custom_code
Instructions to use OpenMOSS-Team/MOSS-TTS-Realtime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-TTS-Realtime with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="OpenMOSS-Team/MOSS-TTS-Realtime", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-TTS-Realtime", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Zhyw0 commited on
Commit ·
7568278
1
Parent(s): 6acbc7f
add: auto_map in config
Browse files- config.json +7 -1
- tokenizer_config.json +4 -1
config.json
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"MossTTSRealtime"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"audio_pad_token": 1024,
|
| 6 |
"audio_vocab_size": 1027,
|
| 7 |
"dtype": "bfloat16",
|
|
@@ -86,7 +93,6 @@
|
|
| 86 |
"tie_word_embeddings": false,
|
| 87 |
"use_cache": true
|
| 88 |
},
|
| 89 |
-
"model_type": "moss_tts_realtime",
|
| 90 |
"reference_audio_pad": 151654,
|
| 91 |
"rvq": 16,
|
| 92 |
"text_pad": 151655,
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_type": "moss_tts_realtime",
|
| 3 |
"architectures": [
|
| 4 |
"MossTTSRealtime"
|
| 5 |
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_mossttsrealtime.MossTTSRealtimeConfig",
|
| 8 |
+
"AutoModel": "modeling_mossttsrealtime.MossTTSRealtime",
|
| 9 |
+
"AutoProcessor": "processing_mossttsrealtime.MossTTSRealtimeProcessor"
|
| 10 |
+
},
|
| 11 |
+
"processor_class": "MossTTSRealtimeProcessor",
|
| 12 |
"audio_pad_token": 1024,
|
| 13 |
"audio_vocab_size": 1027,
|
| 14 |
"dtype": "bfloat16",
|
|
|
|
| 93 |
"tie_word_embeddings": false,
|
| 94 |
"use_cache": true
|
| 95 |
},
|
|
|
|
| 96 |
"reference_audio_pad": 151654,
|
| 97 |
"rvq": 16,
|
| 98 |
"text_pad": 151655,
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"151643": {
|
| 6 |
"content": "<|endoftext|>",
|
|
@@ -233,7 +236,7 @@
|
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
"model_max_length": 131072,
|
| 235 |
"pad_token": "<|endoftext|>",
|
| 236 |
-
"processor_class": "
|
| 237 |
"split_special_tokens": false,
|
| 238 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
"unk_token": null
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
+
"auto_map": {
|
| 5 |
+
"AutoProcessor": "processing_mossttsrealtime.MossTTSRealtimeProcessor"
|
| 6 |
+
},
|
| 7 |
"added_tokens_decoder": {
|
| 8 |
"151643": {
|
| 9 |
"content": "<|endoftext|>",
|
|
|
|
| 236 |
"extra_special_tokens": {},
|
| 237 |
"model_max_length": 131072,
|
| 238 |
"pad_token": "<|endoftext|>",
|
| 239 |
+
"processor_class": "MossTTSRealtimeProcessor",
|
| 240 |
"split_special_tokens": false,
|
| 241 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 242 |
"unk_token": null
|