~ comments

Repositories
Issues
Comments

Results 2 comments of

Training time on VCTK.

Hey, can you tell me about format dataset for multi-speaker, especially folder structure?

running python run.py --config training/config_nsf.yaml --exp_name [model name] --reset returns 'list index out of range' error.

> > `| Hparams chains: ['training/config_nsf.yaml'] | Hparams: K_step: 1000, accumulate_grad_batches: 1, audio_num_mel_bins: 128, audio_sample_rate: 44100, binarization_args: {'shuffle': False, 'with_align': True, 'with_f0': True, 'with_hubert': True, 'with_spk_embed': False, 'with_wav': False}, binarizer_cls:...