Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ Source code for phoneme alignment: https://github.com/sinhprous/F5-TTS/blob/main
|
|
| 16 |
|
| 17 |
Source code for duration predictor: https://github.com/sinhprous/F5-TTS/blob/main/src/f5_tts/model/duration_predictor.py
|
| 18 |
|
|
|
|
|
|
|
| 19 |
## Audio samples
|
| 20 |
Outputs from original model was generated using https://huggingface.co/spaces/mrfakename/E2-F5-TTS
|
| 21 |
The original model usually skips words in these hard texts..
|
|
|
|
| 16 |
|
| 17 |
Source code for duration predictor: https://github.com/sinhprous/F5-TTS/blob/main/src/f5_tts/model/duration_predictor.py
|
| 18 |
|
| 19 |
+
Colab demo: [colab](https://colab.research.google.com/drive/1baUdhv7kIdGIU39VQbeCI_bMAYbyjcF0)
|
| 20 |
+
|
| 21 |
## Audio samples
|
| 22 |
Outputs from original model was generated using https://huggingface.co/spaces/mrfakename/E2-F5-TTS
|
| 23 |
The original model usually skips words in these hard texts..
|