Text-to-Speech
Transformers
ONNX
Safetensors
lingv3_tts
feature-extraction
audio
voice-cloning
multilingual
mixture-of-experts
speech-generation
custom_code
Instructions to use inclusionAI/Ming-3.0-tts-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inclusionAI/Ming-3.0-tts-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="inclusionAI/Ming-3.0-tts-tiny", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("inclusionAI/Ming-3.0-tts-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Correct Tiny backbone parameter description to 7.9B-A1.3B
Browse filesUpdate the subtitle, introduction and parameter table. Preserve model assets and conversion provenance.
README.md
CHANGED
|
@@ -22,7 +22,7 @@ tags:
|
|
| 22 |
<div align="center">
|
| 23 |
<img src="./figures/ant-bailing.png" width="60" alt="Ming-3.0-tts Logo" />
|
| 24 |
<h1>Ming-3.0-tts-tiny</h1>
|
| 25 |
-
<p><i>
|
| 26 |
</div>
|
| 27 |
|
| 28 |
<p align="center">
|
|
@@ -31,7 +31,7 @@ tags:
|
|
| 31 |
<a href="https://modelscope.cn/models/inclusionAI/Ming-3.0-tts-tiny">ModelScope</a>
|
| 32 |
</p>
|
| 33 |
|
| 34 |
-
This repository contains **Ming-3.0-tts-tiny**, the Ming-3.0-tts mixture-of-experts checkpoint built on Ling V3.
|
| 35 |
|
| 36 |
> **Inference requires the [Ming-3.0-tts GitHub repository](https://github.com/inclusionAI/Ming-3.0-tts).** This Hugging Face repository is for checkpoint distribution and does not provide a standalone inference setup. Clone the GitHub repository and follow its README for the current dependencies, inference code and usage instructions. The CLI scripts and Python APIs referenced below are provided by the GitHub repository.
|
| 37 |
|
|
@@ -40,7 +40,7 @@ This repository contains **Ming-3.0-tts-tiny**, the Ming-3.0-tts mixture-of-expe
|
|
| 40 |
| Item | Value |
|
| 41 |
| --- | --- |
|
| 42 |
| Architecture | Mixture of Experts, Ling V3 backbone |
|
| 43 |
-
|
|
| 44 |
| Languages | Chinese, English, German, Spanish, French, Korean, Japanese |
|
| 45 |
| Dialects | Sichuanese, Cantonese |
|
| 46 |
| Python API | `ming_tiny.MingTinyTTS` |
|
|
|
|
| 22 |
<div align="center">
|
| 23 |
<img src="./figures/ant-bailing.png" width="60" alt="Ming-3.0-tts Logo" />
|
| 24 |
<h1>Ming-3.0-tts-tiny</h1>
|
| 25 |
+
<p><i>7.9B-A1.3B multilingual MoE speech synthesis with paralinguistic and free-form control.</i></p>
|
| 26 |
</div>
|
| 27 |
|
| 28 |
<p align="center">
|
|
|
|
| 31 |
<a href="https://modelscope.cn/models/inclusionAI/Ming-3.0-tts-tiny">ModelScope</a>
|
| 32 |
</p>
|
| 33 |
|
| 34 |
+
This repository contains **Ming-3.0-tts-tiny**, the Ming-3.0-tts mixture-of-experts checkpoint built on Ling V3. Its Ling V3 backbone has 7.9B total parameters and activates about 1.3B parameters per token. The repository includes sharded weights, supporting model code, audio tokenizer, speaker encoder and text tokenizer.
|
| 35 |
|
| 36 |
> **Inference requires the [Ming-3.0-tts GitHub repository](https://github.com/inclusionAI/Ming-3.0-tts).** This Hugging Face repository is for checkpoint distribution and does not provide a standalone inference setup. Clone the GitHub repository and follow its README for the current dependencies, inference code and usage instructions. The CLI scripts and Python APIs referenced below are provided by the GitHub repository.
|
| 37 |
|
|
|
|
| 40 |
| Item | Value |
|
| 41 |
| --- | --- |
|
| 42 |
| Architecture | Mixture of Experts, Ling V3 backbone |
|
| 43 |
+
| Backbone parameters | 7.9B total, about 1.3B active per token |
|
| 44 |
| Languages | Chinese, English, German, Spanish, French, Korean, Japanese |
|
| 45 |
| Dialects | Sichuanese, Cantonese |
|
| 46 |
| Python API | `ming_tiny.MingTinyTTS` |
|