yijingshihenxiule comments

Repositories
Issues
Comments

Results 4 comments of


                                            yijingshihenxiule

Audio quality improvements

Hello, @janvainer ! I just train and the audio samples are very noisy now (approx 12 hours 25K epochs on single GPU, batch size 96,). Could you show me your...

[Bug] RuntimeError: min(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.

> Half precision issue, just add dim arg @lucasjinreal Hello, could you please clarify? Need your help! Thank you!

Is it normal to wait a long time between each epoch？

Hello， @HuaHuaOfficial . I encountered the same question. Have you solved it? > At the interval, the GPU does not seem to be working.

how to train hubert-soft content encoder using Mandarin Chinese dataset?

Hi， @joan126 . Have you tried using the pretrained hubert model to extract Mandarin Chinese dataset? Need your help!