YatharthS/MiraTTS
作者 YatharthS ｜ 下载 1.1K ｜ 点赞 186 ｜ 更新 2025-12-24
这个仓库里有什么
- 4 个 ONNX 模型（.onnx 文件）
- 22 个文件，其中 .json 7 个、.onnx 4 个、.wav 3 个、.safetensors 2 个、.md 1 个、.jinja 1 个
- 仓库体积约 1.5 GB
- 最近更新：2025-12-24
ONNX 文件清单
| 文件 | 大小 | 下载 |
|---|---|---|
| decoders/detokenizer.onnx | 184 MB | 下载 |
| decoders/processer.onnx | 83.4 MB | 下载 |
| decoders/q_encoder.onnx | 117 MB | 下载 |
| decoders/s_encoder.onnx | 22.7 MB | 下载 |
怎么用
这些 ONNX 文件可以直接用 ONNX Runtime 加载运行；想先看网络结构，可以把文件上传到 Netron 在线查看器 查看。下载链接指向 Hugging Face 原始文件。
说明文档
MiraTTS
This is the model for the MiraTTS repository. MiraTTS is a high quality TTS model that can generate clear and realistic speech at speeds as fast as 100x realtime.
Key benefits
- Incredibly fast: Over 100x realtime by using Lmdeploy and batching.
- High quality: Generates clear and crisp 48khz audio outputs which is much higher quality then most models.
- Memory efficient: Works within 6gb vram.
- Low latency: Latency can be low as 100ms.
- Voice cloning: Can voice clone any voice with good quality.
Random samples, non cherry picked: <audio controls> <source src="https://huggingface.co/YatharthS/MiraTTS/resolve/main/example2.wav" type="audio/wav"> Your browser does not support the audio element. </audio> <audio controls> <source src="https://huggingface.co/YatharthS/MiraTTS/resolve/main/example3.wav" type="audio/wav"> Your browser does not support the audio element. </audio> <audio controls> <source src="https://huggingface.co/YatharthS/MiraTTS/resolve/main/example1.wav" type="audio/wav"> Your browser does not support the audio element. </audio>
Thanks to Gapeleon for creating a great space for this model, you can try it here: https://huggingface.co/spaces/Gapeleon/Mira-TTS
If you find this model/code helpful, please give a like or star. Thank you.
Please check out the github repo for usage and finetuning notebooks.
模型信息
创建时间: 2025-12-17
更新时间: 2025-12-24
在 Hugging Face 上查看