yl4579/StyleTTS2

Issues

• max_len doesnt crop samples properly

  #290 opened a month ago by FormMe
  0

• Inference latency

  #288 opened 2 months ago by Ananya21162
  5

• Multi-lingual training

  #257 opened 5 months ago by nvadigauvce
  33

• Trained StyleTTS2 for Hindi but didn't get good results

  #286 opened 2 months ago by SandyPanda-MLDL
  7

• `g_loss` is NaN cause of model.predictor_encoder and model.decoder

  #284 opened 2 months ago by xorium
  2

• RuntimeError when try use accelerate finetuning

  #285 opened 2 months ago by dtischencko
  1

• Do we need lr scheduler?

  #274 opened 4 months ago by Dforgeek
  3

• (Q) Multi/Single Speaker different language finetune

  #282 opened 3 months ago by mantrakp04
  7

• In training Stage1 after 49th epoch getting RuntimeError: you can only change requires_grad flags of leaf variables, g_loss.requires_grad = True

  #258 opened 5 months ago by SandyPanda-MLDL
  2

• Training Curves

  #281 opened 3 months ago by atosystem
  3

• Small bug in train_finetune

  #220 opened 8 months ago by Karesto
  2

• Resuming finetuning uses second to last epoch

  #238 opened 7 months ago by SimonDemarty
  1

• HELP WANTED!!!!!!!!!!!

  #235 opened 3 months ago by 21sK1p
  4

• Joint training is failing with Assertion error

  #262 opened 5 months ago by nvadigauvce
  2

• Help Wanted For Stage-1

  #239 opened 6 months ago by xujzouyyz
  3

• asr negative loss

  #236 opened 7 months ago by yijingshihenxiule
  1

• Issue with impropper pauses and random bursts of noise

  #233 opened 7 months ago by king-dahmanus
  1

• Second stage training with smaller window size

  #228 opened 8 months ago by meng2468
  2

• Better LJSpeech or LibriTTS for finetuning a single speaker voice? Or training from scratch with not so much data?

  #226 opened 8 months ago by Sweetapocalyps3
  4

• Getting CUDA Out of memory error in Stage2 training

  #256 opened 3 months ago by SandyPanda-MLDL
  15

• Can anyone please share checkpoints that we get after we complete both stages of training

  #268 opened 5 months ago by tanishbajaj101
  4

• During training, the graphics memory has been continuously increasing

  #242 opened 6 months ago by Wentao795
  1

• What is the chinese phonemizer for pretrained multilinugual PL-BERT?

  #279 opened 3 months ago by YuXiangLin1234
  0

• Very high GPU memory usage in voice cloning after 10-15 runs.

  #222 opened 8 months ago by amssss0
  2

• Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch

  #223 opened 8 months ago by ethan-digi
  3

• Wav File not being read

  #277 opened 4 months ago by MARafey
  0

• ImportError: A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.1

  #275 opened 4 months ago by Geremia
  1

• After training 1 epoch, train_first.py crashes: RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 1, 800]

  #273 opened 4 months ago by fungus75
  1

• StyleTTS Python API doesn't detect devanagari script

  #272 opened 4 months ago by tanishbajaj101
  0

• Can StyleTTS2 use phonemization from different languages to finetune or train?

  #271 opened 4 months ago by tanishbajaj101
  0

• Model Size of fine tuned Model

  #270 opened 5 months ago by deguodedongxi
  0

• SLM Adversarial Training did not start when finetuning

  #227 opened 8 months ago by godspirit00
  13

• weird chinese pronunciation

  #265 opened 5 months ago by SaltedSlark
  3

• Training PL-BERT on styletts2-community/multilingual-pl-bert

  #267 opened 5 months ago by kikozi2000
  0

• Possible Bug in Style Diffusion Inference Code

  #230 opened 5 months ago by brthor
  0

• Questions about Differentiable Duration Modeling

  #264 opened 5 months ago by RoversCode
  1

• In 2nd stage training AttributeError: 'AudioDiffusionConditional' object has no attribute 'module'

  #263 opened 5 months ago by SandyPanda-MLDL
  0

• Can the model learn accents not supported by espeak-ng?

  #261 opened 5 months ago by nigh8w0lf
  0

• Getting error in d_loss.backward() of first_stage training

  #260 opened 5 months ago by SandyPanda-MLDL
  0

• First stage training after 49th epoch (i.e., when epoch >= TMA_epoch)

  #259 opened 5 months ago by SandyPanda-MLDL
  0

• S_loss = 0 ... why?

  #244 opened 6 months ago by DrBrule
  2

• Stage 2 Training Fails with NaN Loss on Single GPU Due to Inconsistent Checkpoint Keys

  #254 opened 6 months ago by 5Hyeons
  0

• Error Message After Using a fine tuned ASR Model

  #252 opened 6 months ago by GUUser91
  0

• FP8 Fine Tuning Crashes

  #248 opened 6 months ago by GUUser91
  1

• Inference Error: context_features exists but no features provided

  #245 opened 6 months ago by JeffryCA
  1

• Speech conditioning like tortoise TTS

  #246 opened 6 months ago by NikitaKononov
  1

• May be a bug? input parameters for model.predictor_encoder and model.style_encoder in train_finetune.py

  #243 opened 6 months ago by starmoon-1134
  0

• Inference with multilingual PL-BERT Model

  #240 opened 6 months ago by deguodedongxi
  4

• Cannot Convert float NaN to integer

  #234 opened 7 months ago by SimonDemarty
  1

• Finetune on ljspeech or libritts?

  #224 opened 8 months ago by Weroxig
  1