search

rishikksh20 / FastSpeech2

PyTorch Implementation of FastSpeech 2 : Fast and High-Quality End-to-End Text to Speech
Apache License 2.0
223 stars 51 forks source link

Train with Muti GPUs #34

Open yujack333 opened 2 years ago

yujack333 commented 2 years ago

Hi, it great job. But i meet some problem when i train with Mutiple GPUs. when i use 4 gpus to train and set the batch size to 256 in train.yaml. the Pitch Loss get 200~400 and the tone is not the same as the speaker. Using single gpu(batch size set 16) to train is ok. Do you have any idear for this problem? do i need change any other parameter when i change the batch size.

rishikksh20 commented 2 years ago

I have never tested for multi-gpu