skol101

Installation nightmare

1

Wow this just boggles my mind how frigging crazy the whole installation process is for vctk preprocess https://github.com/r9y9/deepvoice3_pytorch/tree/master/vctk_preprocess But when you finally get it installed, extract_feats.py just doesn't give a...

I'm fine tuning Hifigan from 2.5ml steps pretrained model to 3ml steps. I wonder if this is the way to go by updating milestones? ``` generator_optimizer_type: Adam generator_optimizer_params: lr: 2.0e-4...

What tools do you use to create/split file lists for new dataset?

1

Please advise as per subject.

Anyone tried adapting this repo to HIFIGAN-2 paper?

1

As per https://pixl.cs.princeton.edu/pubs/Su_2021_HSS/Su-HiFi-GAN-2-WASPAA-2021.pdf

Is TikTok share support

2

If not supported how it can be implemented?

Training on different sampling rates

3

Would be nice if you provided clear instructions on how this model can be trained on different sampling rates.

Subj

num-speakers not yet available for pipx installed package

1

Just installed insanely-fast-whisper today, yet num-speakers not yet available.