search

TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.82k stars 812 forks source link

🥰 Parallel Wavegan now avaiable 😴 #219

Closed dathudeptrai closed 3 years ago

dathudeptrai commented 4 years ago

Parallel Wavegan with tensorflow now supported. Please see here to get more infomation. We strongly recommend the users use pytorch parallel wavegan implementation ParallelWaveGAN to training (very stable) then convert the weight to our tensorflow implementation (see notebook) to accelerate inference speed and enhance deployability. The tensorflow training code is provided but not yet fully test, we tried to train around 150k steps and everything seems fine so far. We would like to thank Tomoki Hayashi for his pytorch parallel wavegan implementation.

ZDisket commented 4 years ago

Multi-band MelGAN G (load from weights) and PWGAN D (from scratch) let me adapt the LJSpeech model to my male speakers in less than 2 hours

stale[bot] commented 3 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.