Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[TTS] add wavernn #1379

Merged
merged 6 commits into from Feb 8, 2022
Merged

Conversation

yt605155624
Copy link
Collaborator

@yt605155624 yt605155624 commented Jan 24, 2022

fix #1324
走通了 wavernn 的动转静

TODO:
1. 验证能否合成声学模型生成的 mel已验证,只是 GANVocoder 输入的 mel 需要 .T 转置一下
2. 看数据预处理是否需要和 GANVocoder 对齐(目前训练的 mel 是没有 norm 的) (目前预处理流程已经和 GANVocoder 保持一致)
3. 验证 MOL 模式
4. 调参

@zh794390558 zh794390558 changed the title [TTS] add wavernn, test=tts [TTS] add wavernn Jan 24, 2022
@yt605155624 yt605155624 added this to the r0.2.0 milestone Jan 24, 2022
examples/csmsc/voc6/conf/default.yaml Outdated Show resolved Hide resolved
examples/csmsc/voc6/conf/default.yaml Show resolved Hide resolved
examples/csmsc/voc6/conf/default.yaml Outdated Show resolved Hide resolved
examples/csmsc/voc6/conf/default.yaml Outdated Show resolved Hide resolved
examples/csmsc/voc6/local/preprocess.sh Show resolved Hide resolved
paddlespeech/t2s/models/wavernn/wavernn.py Outdated Show resolved Hide resolved
paddlespeech/t2s/models/wavernn/wavernn.py Outdated Show resolved Hide resolved
paddlespeech/t2s/models/wavernn/wavernn.py Show resolved Hide resolved
paddlespeech/t2s/models/wavernn/wavernn.py Outdated Show resolved Hide resolved
paddlespeech/t2s/models/wavernn/wavernn.py Show resolved Hide resolved
Copy link
Collaborator

@zh794390558 zh794390558 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@zh794390558 zh794390558 merged commit dcfc32f into PaddlePaddle:develop Feb 8, 2022
@yt605155624 yt605155624 deleted the new_wavernn branch February 28, 2022 06:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

[tts] vocoder - WaveRNN
2 participants