You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi @projetmbc,
If you can find any French speech dataset, you would be possible to train the model on your own.
To train on your own dataset, you may need to obtain the duration labels using tools like [Montreal Forced Aligner](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner). And be sure that the dataset is in the same format with the LJSpeech dataset, or you may need to modify the `TextAudioLoaderWithDuration` to load your own dataset.
Is it possible to obtain French audio?
The text was updated successfully, but these errors were encountered: