Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ base_model:
|
|
| 6 |
- yl4579/StyleTTS2-LibriTTS
|
| 7 |
pipeline_tag: text-to-speech
|
| 8 |
---
|
|
|
|
|
|
|
| 9 |
This model is a direct ONNX conversion of [yl4579/StyleTTS2-LibriTTS](https://huggingface.co/yl4579/StyleTTS2-LibriTTS) without modification to its weights and therefore inherits the [original license](https://github.com/yl4579/StyleTTS2?tab=readme-ov-file#license). It currently powers a [WebUI that performs TTS inference on CPU](https://hexgrad.com/). To facilitate lazy loading, it is chunked into four parts.
|
| 10 |
|
| 11 |
The original PyTorch checkpoint, trained on a subset of LibriTTS by the authors of StyleTTS 2, can be considered a "base model", and it has some limitations. That base model should not be confused with Kokoro, a StyleTTS 2 variant using a different decoder architecture, which is currently only being hosted at [https://hf.co/spaces/hexgrad/Kokoro-TTS](https://hf.co/spaces/hexgrad/Kokoro-TTS).
|
|
|
|
| 6 |
- yl4579/StyleTTS2-LibriTTS
|
| 7 |
pipeline_tag: text-to-speech
|
| 8 |
---
|
| 9 |
+
**This repository is a fossil.**
|
| 10 |
+
|
| 11 |
This model is a direct ONNX conversion of [yl4579/StyleTTS2-LibriTTS](https://huggingface.co/yl4579/StyleTTS2-LibriTTS) without modification to its weights and therefore inherits the [original license](https://github.com/yl4579/StyleTTS2?tab=readme-ov-file#license). It currently powers a [WebUI that performs TTS inference on CPU](https://hexgrad.com/). To facilitate lazy loading, it is chunked into four parts.
|
| 12 |
|
| 13 |
The original PyTorch checkpoint, trained on a subset of LibriTTS by the authors of StyleTTS 2, can be considered a "base model", and it has some limitations. That base model should not be confused with Kokoro, a StyleTTS 2 variant using a different decoder architecture, which is currently only being hosted at [https://hf.co/spaces/hexgrad/Kokoro-TTS](https://hf.co/spaces/hexgrad/Kokoro-TTS).
|