Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BreezyVoice
|
| 2 |
+
|
| 3 |
+
BreezyVoice is a voice-cloning text-to-speech system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities via auxiliary 注音 (bopomofo) inputs.
|
| 4 |
+
|
| 5 |
+
[Playground](); [GitHub](); [Paper]()
|
| 6 |
+
|
| 7 |
+
## Run
|
| 8 |
+
|
| 9 |
+
**Running from the GitHub instruction automatically downloads the model for you**
|
| 10 |
+
|
| 11 |
+
You can also run the model from a specified local path by cloning the model
|
| 12 |
+
```
|
| 13 |
+
git lfs install
|
| 14 |
+
git clone https://huggingface.co/MediaTek-Research/BreezyVoice-300M
|
| 15 |
+
```
|
| 16 |
+
then, you can use the model as specified in the run_inference.py script, providing the local model path using the model_path parameter.
|
| 17 |
+
|
| 18 |
+
If you like our work, please cite:
|
| 19 |
+
|
| 20 |
+
|