jaywalnut310/vits

Issues

• Code doesn;t even run. so many errors intalling pip

  #213 opened a year ago by thenaivekid
  7

• When I run train_ms.py on WSL2 get CUDA error and something.

  #224 opened 8 months ago by ramune64
  0

• ETAs for training?

  #223 opened 8 months ago by IngwiePhoenix
  2

• Runtime error

  #221 opened a year ago by SameerSri72
  1

• Continue training VITS

  #211 opened a year ago by Pipe1213
  2

• progress keeps resetting, checkpoint fails to load properly

  #186 opened 2 years ago by RonFusaishi
  1

• getting Index error: dimension out of range (expected to be in range of [-1,0], but got got 1

  #217 opened a year ago by SameerSri72
  4

• 显存占用很高

  #222 opened a year ago by Gooddz1
  0

• VITS codes failed to run for Python 3.10.12

  #187 opened 2 years ago by CKAbundant
  2

• 是否可以通过java去实现训练和推理？

  #219 opened a year ago by yuanliuzhizi
  1

• License Question

  #220 opened a year ago by UmerrAhsan
  0

• VITS model Conversion to ONNX and TFLite.

  #206 opened 2 years ago by tusharhchauhan
  2

• can we calculate text'phoneme duration time form StochasticDurationPredictor or DurationPredictor ?

  #218 opened a year ago by CasonTsai
  0

• intersperse function explain

  #216 opened a year ago by chnk58hoang
  0

• Flip module explain

  #214 opened a year ago by chnk58hoang
  1

• RTX4090 training is very slow. Is there something wrong with my parameters?

  #197 opened 2 years ago by Tsangchi-Lam
  3

• Option for Single GPU?

  #204 opened 2 years ago by hoomexsun
  2

• anyway the "weight.data.zero_()","bias.data.zero_()" just for example or real code using?

  #215 opened a year ago by FMzzq
  0

• 有大佬知道训练集有部分数据没有生成.spec.pt文件是什么原因？

  #207 opened 2 years ago by jin1258804025
  3

• having numpy complex error

  #199 opened 2 years ago by M-Usamah
  1

• Issues with VITS: Mixed Voices and Missing Number Synthesis

  #212 opened a year ago by iliuha93
  0

• No audio generated

  #210 opened 2 years ago by zhouhao27
  0

• Can't install requirement

  #209 opened 2 years ago by zhouhao27
  1

• Multi node Support

  #208 opened 2 years ago by Ahmed-Hossam-Aldeen
  0

• segmentation fault after train a few steps

  #181 opened 2 years ago by zhufeijuanjuan
  6

• Transfer learning and fine-tuning tts

  #191 opened 2 years ago by ToiYeuTien
  3

• Help me! Errors in the training process of vits for other datasets

  #205 opened 2 years ago by zazachao
  0

• Is there a way to do batch inference?

  #190 opened 2 years ago by SoulflareRC
  3

• [CONTRIBUTION] Speech Dataset Generator

  #203 opened 2 years ago by davidmartinrius
  0

• NCCL error windows

  #202 opened 2 years ago by Vubni
  1

• Problems adding a new speaker

  #200 opened 2 years ago by JoanisTriandafilidi
  0

• How is the Out of Dictionary texts created?

  #201 opened 2 years ago by deep-convai
  0

• How to use trained model in inference?

  #193 opened 2 years ago by solee0022
  2

• [Question] about improve quality audio

  #198 opened 2 years ago by phamkhactu
  0

• Duration Issue with the generated audio

  #175 opened 2 years ago by Aliasgarsaifee
  3

• Negative loss_dur

  #196 opened 2 years ago by staceystaceystacey
  1

• Fine-tune with multiple speakers' data.

  #195 opened 2 years ago by soominjung
  0

• DistributedBucketSampler : create bucket sampler issue.

  #194 opened 2 years ago by YoungJae98
  1

• How to locate the spreak time of each word

  #192 opened 2 years ago by huwenkai26
  0

• Some of the losses increasing during training?

  #189 opened 2 years ago by pouryajafarzadeh
  0

• How to continue training from the previous stopped epoch?

  #188 opened 2 years ago by ctimict
  1

• Peak Performance of Single vs. Multi-Speaker TTS Models: Seeking Insights and References

  #185 opened 2 years ago by ikpark09
  0

• Training time too long

  #184 opened 2 years ago by newton2149
  0

• RuntimeError: CUDA error: unknown error and torch.multiprocessing.spawn.ProcessRaisedException

  #182 opened 2 years ago by daayaa
  1

• 大佬们救救我 AttributeError: 'DistributedDataParallel' object has no attribute 'infer' 报错

  #183 opened 2 years ago by aaqq112
  1

• running vits on Ventura GPU

  #180 opened 2 years ago by dnabanita7
  1

• Can I also train an Italian model?

  #179 opened 2 years ago by Pnlvfx
  0

• Is there some way to force a break?

  #178 opened 2 years ago by vidigal
  0

• Iserting new symbols in a pre-trained model

  #177 opened 2 years ago by vidigal
  0

• Issue with training at 8000Hz

  #176 opened 2 years ago by athenasaurav
  0