KimythAnly / AGAIN-VC

This is the official implementation of the paper AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization.

https://kimythanly.github.io/AGAIN-VC-demo/index

MIT License

111 stars 19 forks source link

关于生成语音的时长和速度 #14

Closed fb029ed closed 2 years ago

fb029ed commented 2 years ago

您好，关于生成的语音想咨询您一下：根据readme给出的inference步骤

Example

python inference.py \ -c config/train_again-c4s.yaml \ -l checkpoints/again/c4s \ -s data/wav48/p225/p225_001.wav \ -t data/wav48/p226/p226_001.wav \ -o data/generated 其中train_again-c4s.yaml 未更改，checkpoints/again/c4s使用的是repo提供的预训练模型。运行生成的语音语速很快，时长大约是src语音的一半，请问是否正常。感谢

fb029ed commented 2 years ago

librosa.effects.trim静音消除阈值设置严格导致去电了较多的有效片段，已解决。