Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
README.md | 2021-03-10 | 405 Bytes | |
v0.2.0.tar.gz | 2021-03-10 | 209.3 kB | |
v0.2.0.zip | 2021-03-10 | 269.1 kB | |
Totals: 3 Items | 478.8 kB | 0 |
Experiemnts conducted with LJSpeech dataset are extended, from separate ones for acoustic models and vocoders, to chained ones. Neural acoustic models with neural vocoders work togather to make a simpler TTS pipeline.
- Transformer TTS + Waveflow;
- Tacotron2 + Waveflow.
Since the acoustic configurations for training the acoustic model and the vocoder is the same, chaining them is seamless.