Update README.md
Browse files
README.md
CHANGED
|
@@ -9,4 +9,8 @@ XTTSv2 checkpoints finedtuned with the forked Coqui TTS (https://github.com/idia
|
|
| 9 |
|
| 10 |
Trained using the Indic TTS Database (https://www.iitm.ac.in/donlab/tts/) and Mozilla Common Voice 18.0 Hindi dataset (https://commonvoice.mozilla.org/en/datasets)
|
| 11 |
|
| 12 |
-
Rename checkpoint to model.pth and replace original XTTSv2 model, or use according to how your implementation of XTTSv2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
Trained using the Indic TTS Database (https://www.iitm.ac.in/donlab/tts/) and Mozilla Common Voice 18.0 Hindi dataset (https://commonvoice.mozilla.org/en/datasets)
|
| 11 |
|
| 12 |
+
Rename checkpoint to model.pth and replace original XTTSv2 model, or use according to how your implementation of XTTSv2.
|
| 13 |
+
|
| 14 |
+
The checkpoints with the highest step count may _not be the best_. I think the best quality output here is best_model_43036.pth Reference speaker audio files are in ./speakers-hi of this repo
|
| 15 |
+
|
| 16 |
+
Use language code 'hi' at inference for Hindi speech, use language code 'hi' with English text to generate English with the learned Hindi pronounciations.
|