OlaWod/FreeVC

Issues

• Poor results with: voice_conversion_models--multilingual--vctk--freevc24.zip CoquiTTS

  #89 opened 10 months ago by ballerburg9005
  5

• 转换后音色跟着 source 而不是 target

  #97 opened 2 months ago by Blakey-Gavin
  10

• 训练了500个epoch，按照freevc.json配置进行训练，无论wav_tgt使用何种音色，测试出来的音色都是同一个？

  #77 opened 2 years ago by pigzach
  1

• 音色转换程度不一致

  #74 opened 2 years ago by liubin3702
  1

• 用free-vc-s的时候，发现convert.py和train时候的data_utils.py中的数据处理不一致

  #96 opened 2 months ago by zxj329
  0

• 为什么训练的时候会出现min value和max value的打印

  #95 opened 2 months ago by zxj329
  0

• Fine Tune with My Data

  #94 opened 2 months ago by Blakey-Gavin
  0

• About checkpoint

  #91 opened 7 months ago by Sunny-Liyq
  2

• The audio suffix of VCTK data set is not '_ mic2.flac'？

  #66 opened 2 years ago by 15755841658
  3

• Killed on Linux

  #92 opened 5 months ago by Tiaranso
  0

• Error while finetuning

  #56 opened a year ago by MaN0bhiR
  10

• Unseen Male to Male results in Female output

  #73 opened 2 years ago by bharaniyv
  1

• 48khz

  #63 opened 2 years ago by steven850
  38

• Why is the speaker embedding g used to condition the Posterior Encoder and the Decoder?

  #88 opened a year ago by st-vincent1
  0

• training a model with 44.1k data

  #87 opened a year ago by clumsyroot
  0

• target pitch issue after training (not appearing if using the pretrained checkpoint)

  #85 opened a year ago by fervillamar
  1

• How to start inference example?

  #83 opened a year ago by asusdisciple
  1

• Config file for the FreeVC-24 checkpoint

  #86 opened a year ago by XinleiNIU
  1

• poor performance on seen-to-unseen task while finetuning on Hindi language

  #79 opened 2 years ago by rgenai
  2

• 关于训练问题

  #84 opened a year ago by Aydous
  0

• Fine tuning with custom (multilingual) data

  #82 opened a year ago by ukemamaster
  1

• Vocoder version

  #81 opened a year ago by Blakey-Gavin
  0

• Condition decoder on desired output length to have control over speech rate in inference?

  #70 opened a year ago by bejaeger
  0

• About Chinese ssl feature?

  #62 opened 2 years ago by WhiteFu
  3

• Slow training speed

  #61 opened 2 years ago by lsw5835
  4

• 2023.01.10 update: code below can deteriorate model performance

  #80 opened 2 years ago by Dannynis
  3

• 关于算法的类型

  #76 opened 2 years ago by Yaodada12
  1

• Can you explain the meaning of prior encoder?

  #64 opened 2 years ago by chenzh99
  1

• Changing batch size to 16 or 32

  #78 opened 2 years ago by Peleg-Bruck
  0

• Epoch duration

  #75 opened 2 years ago by Peleg-Bruck
  0

• Inference or train with WavLM-Base or WavLM-Base+?

  #69 opened 2 years ago by khacanh
  1

• 基于您现有的模型使用aishell3训练，大概要训练多久，作者有试过吗

  #71 opened 2 years ago by liubin3702
  0

• Question for hps.data.n_mel_channels

  #67 opened 2 years ago by lsw5835
  0

• Asking help for understanding code.

  #65 opened 2 years ago by chenzh99
  0

• Extreme distortion in multi-lingual voice conversion

  #53 opened 2 years ago by AdityaVishwakarmaIN
  1

• Error with 24khz data utils

  #57 opened 2 years ago by steven850
  27

• Robotic noise on audio

  #60 opened 2 years ago by Likkkez
  4

• Training Log for 24khz

  #47 opened 2 years ago by steven850
  4

• Segmentation fault while training

  #58 opened 2 years ago by Likkkez
  3

• Model Resolution

  #54 opened 2 years ago by steven850
  1

• s-o-p pronunciation , high-low tone distortion

  #51 opened 2 years ago by lsw5835
  5

• Question about SR,SPK preprocess in 24khz

  #55 opened 2 years ago by LeMoyenAge
  2

• SR questions

  #52 opened 2 years ago by steven850
  2

• notebook Google Colab

  #43 opened 2 years ago by HobisPL
  6

• Training using LibriTTS

  #50 opened 2 years ago by lsw5835
  2

• WHAMR! artificial reverberation

  #48 opened 2 years ago by Ashraf-Ali-aa
  3

• 48k voice conversion

  #45 opened 2 years ago by lsw5835
  2

• SR Process

  #49 opened 2 years ago by Shmuel-Gruel
  2

• Improving Target speaker conversion

  #46 opened 2 years ago by Ashraf-Ali-aa
  1

• About Speaker Embeddings

  #44 opened 2 years ago by Shmuel-Gruel
  4