AdaIN-VC speaker encoder support

ming024 / FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

MIT License

1.84k stars 535 forks source link

AdaIN-VC speaker encoder support #31

Closed HudsonHuang closed 3 years ago

HudsonHuang commented 3 years ago

Hi, thank you for your work, it's awesome.

I participated in your lecture about M2VoC. You shared the approach of using AdaIN-VC as speaker encoder, it was impressive. But the code here seems to only support lookup tables, any plan for it? https://github.com/ming024/FastSpeech2/blob/76b2b657262b645898ec9db0a1eb6ff2319cfee6/model/fastspeech2.py#L38

ming024 commented 3 years ago

@HudsonHuang please refer to the "M2VoC" branch for the code used in the M2VoC challenge. However, I did not put the code of AdaIN-VC in this repository. You can check AdaIN-VC for the implementation detail. I did not do any modification in addition to the mel-spectrogram preprocessing.

ming024 commented 3 years ago

Closed #31