wenyuc55

Hi, when I was training the code, I couldn't separate all ten audios. Only the first audio could be separated, but the second one couldn't be separated. If I change...

Program memory segmentation error (core dumped) for training LibriMix

1

### Describe the bug I execute the contents of the LibriMix folder. However, I encountered the problem of program memory segmentation error (core dumped) during training. ...

Training problem: KeyError: 'scale_invariant_signal_noise_ratio'

1

I have done the training step now, but now I get an error (wave-env) ziyu@ziyu:~/桌面/wenyu/Waveformer/Waveformer-main$ python3 -W ignore -m src.training.train experiments/dcc_tf_ckpt_E256_10_D128_1 --use_cuda Imported the model from 'src.training.dcc_tf'. Loading train dataset:...

Encountered a TypeError: expected string or bytes-like object when training the model using dual-GPU model sharding.

4

### Describe the bug Originally, I used a single 4090 GPU to train the 4-speaker LibriMix model and had prepared my own mixed datasets. I noticed that training results with...