winddori2002/TriAAN-VC

Issues

• Chinese voice conversion

  #24 opened 7 months ago by lareina-a
  0

• a question about the evaluation results

  #23 opened 8 months ago by kay9012
  3

• about base.yaml

  #22 opened 10 months ago by wangsheng3
  0

• A question about speaker encoder

  #21 opened a year ago by bigdan12
  1

• Memory issue/bug

  #18 opened a year ago by asusdisciple
  2

• resluts

  #16 opened a year ago by Blakey-Gavin
  15

• question about model size and result

  #17 opened a year ago by JeffC0628
  3

• is this better than so-vit-svc rvc?

  #15 opened 2 years ago by loboere
  1

• Model output size

  #14 opened 2 years ago by Shmuel-Gruel
  1

• Evaluation results

  #13 opened 2 years ago by Blakey-Gavin
  3

• Mixed datasets and calculate the threshold value

  #12 opened 2 years ago by Blakey-Gavin
  3

• Training Logs

  #11 opened 2 years ago by Shmuel-Gruel
  2

• Training time/compute for provided model

  #3 opened 2 years ago by nateraw
  3

• Other vocoder or any possible improvement

  #10 opened 2 years ago by Souvic
  1

• VCTK dataset ASV threhold vaule code

  #9 opened 2 years ago by predawnang
  1

• What is st and ut?

  #8 opened 2 years ago by Souvic
  2

• changing window size and n_fft

  #7 opened 2 years ago by Souvic
  2

• Silence trimming code

  #6 opened 2 years ago by Souvic
  2

• can you suggest settings for 16000hz sample rate and n_fft 1024 training

  #5 opened 2 years ago by bharaniyv
  7

• Can I train on one long audio file (10 mins+)?

  #4 opened 2 years ago by moaazassali
  4

• Custom Traning

  #2 opened 2 years ago by carlosedubarreto
  2

• FileNotFoundError: [Errno 2] No such file or directory: './base_data/mel_stats.npy'

  #1 opened 2 years ago by carlosedubarreto
  3