PlayVoice/lora-svc

Issues

• ValueError: not enough values to unpack (expected 4, got 1)

  #63 opened 4 months ago by IsEddy
  4

• audio examples

  #92 opened a year ago by easypx
  1

• whisper-v3 got open sourced

  #95 opened a year ago by 0mis
  0

• Confused

  #94 opened a year ago by KeystoneScience
  1

• Training is ineffective, the generator's loss is only around 5,000

  #93 opened a year ago by NLPV2011
  0

• .

  #89 opened a year ago by Bingtai1015
  0

• data_raw

  #91 opened a year ago by h310558606
  0

• DataSet

  #90 opened a year ago by h310558606
  0

• Diff-svc, so-vits-svc效果对比

  #58 opened 2 years ago by yygg678
  6

• num_samples=0

  #88 opened a year ago by sergedahdouh
  2

• incorrect audio shape

  #87 opened a year ago by sergedahdouh
  1

• you implementing vocos?

  #68 opened a year ago by 0mis
  3

• 换了台 Tesla P40 来跑，结果出错了

  #56 opened 2 years ago by krysof
  1

• I have a question about using lora for fine-tuning

  #64 opened 2 years ago by h0ngc
  4

• `svc_preprocess_f0.py` rootPath should be changed to 48k?

  #62 opened 2 years ago by edwardmfho
  1

• 音色是否可以融合或者调整

  #61 opened 2 years ago by suzhenghang
  1

• 训练一切正常，但是保存第一个模型时出现了ZeroDivisionError: float division by zero

  #60 opened 2 years ago by sswwjj4
  2

• Missing speaker file

  #40 opened 2 years ago by nskwal
  1

• Training sample size

  #57 opened 2 years ago by jinsu35
  1

• 杂音很重

  #55 opened 2 years ago by cooldoomsday
  10

• 请问48K比特率是否是24bit？

  #54 opened 2 years ago by lianganbin
  20

• 16k和48k的二选一还是两种都要？

  #49 opened 2 years ago by ccimage
  8

• SpeakerAdapter

  #53 opened 2 years ago by yygg678
  1

• 人声克隆

  #52 opened 2 years ago by suzhenghang
  0

• ValueError: zero-size array to reduction operation maximum which has no identity

  #51 opened 2 years ago by Desuka-art
  0

• 再弱弱的问一个问题，训练到多少算是完成的？

  #48 opened 2 years ago by krysof
  19

• 弱弱的问下，推理时如何能升降调。。。

  #47 opened 2 years ago by krysof
  2

• 如果想训练更高采样率的预训练模型有参考的参数吗

  #41 opened 2 years ago by KakaruHayate
  4

• 执行音质增强时提示：HifiGAN model file is not found!

  #46 opened 2 years ago by fatinghenji
  1

• 推理时指定--statics参数，生成的音频为空白

  #45 opened 2 years ago by ayanesakura
  2

• 执行频率扩展时遇到严重性能问题

  #44 opened 2 years ago by fatinghenji
  1

• 声音沙哑是怎么回事

  #43 opened 2 years ago by syaofox
  5

• readme中展示的日志应该如何查看

  #42 opened 2 years ago by ayanesakura
  2

• 在已经完成一定训练后如何继续训练

  #38 opened 2 years ago by xiank1
  3

• 您好，请问混响怎么去掉？

  #27 opened 2 years ago by qiuyuzhao
  4

• Error when trying to infer a file

  #24 opened 2 years ago by Desuka-art
  5

• U

  #33 opened 2 years ago by ToToughToDie
  0

• ZeroDivisionError: float division by zero

  #26 opened 2 years ago by loboere
  11

• 这个是显存不够吗？

  #32 opened 2 years ago by Chromer163
  3

• 高音崩掉了

  #34 opened 2 years ago by FlyToYourMooN
  7

• 感觉可以接一个hifigan-bwe超采样下？

  #31 opened 2 years ago by KakaruHayate
  7

• 这里可能为空, 如果为空的时候需要跳过

  #35 opened 2 years ago by kasuganosora
  1

• 关于训练集疑问

  #30 opened 2 years ago by suzhenghang
  1

• 音色融合请教

  #29 opened 2 years ago by WhiteFu
  2

• 关于歌声转换的疑问

  #28 opened 2 years ago by shr-go
  1

• 能否提供数据集准备教程及训练时的注意事项与心得？

  #23 opened 2 years ago by DLSeed
  3

• librosa.util.exceptions.ParameterError: Audio buffer is not finite everywhere

  #22 opened 2 years ago by Desuka-art
  0

• Can someone help me through discord?

  #20 opened 2 years ago by Desuka-art
  18

• Help!

  #25 opened 2 years ago by justinjohn0306
  3

• Need a little help with resolving this error on my Windows machine

  #21 opened 2 years ago by justinjohn0306
  1