yl4579 StyleTTS2 issues

yl4579 / StyleTTS2

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

MIT License

4.97k stars 419 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Add Replicate demo link

#295 deepfates opened 20 hours ago
0
Need advice and potenital help.

#294 PrarthanAgarwal opened 22 hours ago
0
TensorRT Optimization

#293 nityanandmathur opened 2 weeks ago
1
When cloning, how can we make the generated multiple audios consistent?

#292 dnlzsy opened 2 weeks ago
1
Is there a GUI for training?

#291 juangea opened 2 weeks ago
1
max_len doesnt crop samples properly

#290 FormMe opened 4 weeks ago
3
Neuralvox merge

#289 gilbertgong closed 1 month ago
0
Inference latency

#288 Ananya21162 opened 1 month ago
6
Trained StyleTTS2 for Hindi but didn't get good results

#286 SandyPanda-MLDL opened 1 month ago
7
RuntimeError when try use accelerate finetuning

#285 dtischencko closed 1 month ago
1
`g_loss` is NaN cause of model.predictor_encoder and model.decoder

#284 xorium closed 1 month ago
2
(Q) Multi/Single Speaker different language finetune

#282 mantrakp04 opened 2 months ago
7
Training Curves

#281 atosystem opened 2 months ago
3
What is the chinese phonemizer for pretrained multilinugual PL-BERT?

#279 YuXiangLin1234 opened 3 months ago
0
[GARDENING]: Freeze package versions

#278 pranav-vijayakumarrao-techlabs closed 3 months ago
0
Wav File not being read

#277 MARafey closed 3 months ago
0
Fix weird pulse at the end of the model

#276 ZZDoog opened 3 months ago
0
ImportError: A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.1

#275 Geremia closed 3 months ago
1
Do we need lr scheduler?

#274 Dforgeek opened 4 months ago
3
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 fungus75 opened 4 months ago
1
StyleTTS Python API doesn't detect devanagari script

#272 tanishbajaj101 opened 4 months ago
0
Can StyleTTS2 use phonemization from different languages to finetune or train?

#271 tanishbajaj101 opened 4 months ago
0
Model Size of fine tuned Model

#270 deguodedongxi opened 4 months ago
0
Refactored code for improved readability and performance

#269 zolero closed 1 month ago
0
Can anyone please share checkpoints that we get after we complete both stages of training

#268 tanishbajaj101 opened 4 months ago
4
Training PL-BERT on styletts2-community/multilingual-pl-bert

#267 kikozi2000 opened 4 months ago
0
weird chinese pronunciation

#265 SaltedSlark opened 4 months ago
3
Questions about Differentiable Duration Modeling

#264 RoversCode opened 4 months ago
1
In 2nd stage training AttributeError: 'AudioDiffusionConditional' object has no attribute 'module'

#263 SandyPanda-MLDL opened 4 months ago
0
Joint training is failing with Assertion error

#262 nvadigauvce opened 4 months ago
2
Can the model learn accents not supported by espeak-ng?

#261 nigh8w0lf opened 5 months ago
0
Getting error in d_loss.backward() of first_stage training

#260 SandyPanda-MLDL opened 5 months ago
0
First stage training after 49th epoch (i.e., when epoch >= TMA_epoch)

#259 SandyPanda-MLDL opened 5 months ago
0
In training Stage1 after 49th epoch getting RuntimeError: you can only change requires_grad flags of leaf variables, g_loss.requires_grad = True

#258 SandyPanda-MLDL opened 5 months ago
2
Multi-lingual training

#257 nvadigauvce opened 5 months ago
33
Getting CUDA Out of memory error in Stage2 training

#256 SandyPanda-MLDL closed 2 months ago
15
Stage 2 Training Fails with NaN Loss on Single GPU Due to Inconsistent Checkpoint Keys

#254 5Hyeons opened 5 months ago
0
feat: Improve model checkpoint loading

#253 5Hyeons opened 5 months ago
0
Error Message After Using a fine tuned ASR Model

#252 GUUser91 opened 5 months ago
0
Test trt

#249 siddhatiwari closed 5 months ago
0
FP8 Fine Tuning Crashes

#248 GUUser91 opened 5 months ago
1
Train finetune logging

#247 zjaffal closed 5 months ago
0
Speech conditioning like tortoise TTS

#246 NikitaKononov opened 5 months ago
1
Inference Error: context_features exists but no features provided

#245 JeffryCA closed 5 months ago
1
S_loss = 0 ... why?

#244 DrBrule closed 5 months ago
2
May be a bug? input parameters for model.predictor_encoder and model.style_encoder in train_finetune.py

#243 starmoon-1134 opened 5 months ago
0
During training, the graphics memory has been continuously increasing

#242 Wentao795 opened 5 months ago
1
Inference with multilingual PL-BERT Model

#240 deguodedongxi closed 5 months ago
4
Help Wanted For Stage-1

#239 xujzouyyz opened 6 months ago
3
Resuming finetuning uses second to last epoch

#238 SimonDemarty opened 6 months ago
1