maum-ai/voicefilter

Issues

• What is the term spk refers to in the below code ? line 127

  #33 opened 2 years ago by kirupa65
  0

• how to work for multi noise

  #32 opened 2 years ago by yhbembedding
  0

• Training setting problem

  #25 opened 4 years ago by Morank88
  6

• Can you get the initial mean SDR on LibriSpeech using Google's test list?

  #20 opened 5 years ago by weedwind
  8

• Cannot reproduce reported SDR & retrain the speaker embedding

  #30 opened 3 years ago by nnbtam
  0

• VoiceFilter realization problem

  #5 opened 6 years ago by va-volokhov
  8

• Question about wav2spec function in utils/audo.py

  #29 opened 3 years ago by HieDean
  0

• question about ffmpeg-normalize

  #28 opened 4 years ago by somepayphone
  0

• Question about utils/evaluation.py

  #13 opened 5 years ago by lawlict
  2

• Real-time inference

  #3 opened 6 years ago by kyungjin-lee
  4

• Can I get the pretrained model please! I so dearly need it for my project, here's my email just in case, iit2019013@iiita.ac.in

  #24 opened 4 years ago by batnik1
  1

• Is the VoiceFilter model checkpoint available to be used directly?

  #26 opened 4 years ago by salonijain18
  1

• fianl model

  #7 opened 6 years ago by 0ifeng0
  7

• inference

  #23 opened 5 years ago by kurbobo
  0

• the model implementation comprehension

  #22 opened 5 years ago by kurbobo
  1

• Question about normalize-resample.sh

  #10 opened 6 years ago by yxixi
  4

• hop_length and win_length

  #21 opened 5 years ago by ksellesk
  0

• embedder.pt with new dataset

  #19 opened 5 years ago by Devid29
  4

• Question when training VoiceFilter

  #12 opened 5 years ago by yxixi
  1

• Out of memory when Inferencing a single file.

  #4 opened 6 years ago by BhaveshDevjani
  5

• Need to try power-law compression loss

  #14 opened 5 years ago by seungwonpark
  2

• Question about start point of SDR

  #9 opened 5 years ago by lycox1
  4

• Question when preprocessing wav files

  #11 opened 5 years ago by yxixi
  1

• how to create file embedder

  #8 opened 6 years ago by giappham
  5

• The files from the dataset are in flac format

  #2 opened 6 years ago by BhaveshDevjani
  3

• Try partial convolution padding scheme

  #1 opened 6 years ago by seungwonpark
  1