forked fromfatchord/WaveRNN
- Notifications
You must be signed in to change notification settings - Fork37
erogol/WaveRNN
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
This code is forked fromhttps://github.com/fatchord/WaveRNN and optimized forMozilla-TTS.
| Models | Dataset | Commit | Audio Sample | TTS model | Details |
|---|---|---|---|---|---|
| mold model | LJspeech | 8a1c152 | soundcloud | Tacotron2-iter-260K | Model with Mixture of Logistic Distribution |
| 10bit model | LJSpeech | faea90b | soundcloud | Tacotron2-iter-260K | 10bit Softmax output |
| universal vocoder | LibriTTS | 12c8744 | soundcloud | - | (details) |
Check thisTTS notebook to see TTS+WaveRNN in action.To train your own model, you can useExtractTTSSpectrogram to generate spectrograms by TTS and train WaveRNN.It might be also interesting to check thisTTS issue to catchup with the current state.