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

4.37k stars 340 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

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

#261 nigh8w0lf opened 4 days ago
0
Getting error in d_loss.backward() of first_stage training

#260 SandyPanda-MLDL opened 4 days ago
0
First stage training after 49th epoch (i.e., when epoch >= TMA_epoch)

#259 SandyPanda-MLDL opened 4 days 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 4 days ago
0
Multi-lingual training

#257 nvadigauvce opened 5 days ago
8
Getting CUDA Out of memory error in Stage2 training

#256 SandyPanda-MLDL opened 1 week ago
13
Stage 2 Training Fails with NaN Loss on Single GPU Due to Inconsistent Checkpoint Keys

#254 5Hyeons opened 2 weeks ago
0
feat: Improve model checkpoint loading

#253 5Hyeons opened 2 weeks ago
0
Error Message After Using a fine tuned ASR Model

#252 GUUser91 opened 2 weeks ago
0
Test trt

#249 siddhatiwari closed 2 weeks ago
0
FP8 Fine Tuning Crashes

#248 GUUser91 opened 3 weeks ago
1
Train finetune logging

#247 zjaffal closed 3 weeks ago
0
Speech conditioning like tortoise TTS

#246 NikitaKononov opened 3 weeks ago
1
Inference Error: context_features exists but no features provided

#245 JeffryCA closed 3 weeks ago
1
S_loss = 0 ... why?

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

#243 starmoon-1134 opened 1 month ago
0
During training, the graphics memory has been continuously increasing

#242 Wentao795 opened 1 month ago
0
Inference with multilingual PL-BERT Model

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

#239 xujzouyyz opened 1 month ago
2
Resuming finetuning uses second to last epoch

#238 SimonDemarty opened 1 month ago
0
Code organization (train_first.py and related utils)

#237 astricks closed 1 month ago
1
asr negative loss

#236 yijingshihenxiule opened 1 month ago
0
HELP WANTED!!!!!!!!!!!

#235 21sK1p opened 1 month ago
3
Cannot Convert float NaN to integer

#234 SimonDemarty closed 1 month ago
1
Issue with impropper pauses and random bursts of noise

#233 king-dahmanus opened 2 months ago
0
Possible Bug in Style Diffusion Inference Code

#230 brthor opened 2 months ago
0
Update training scripts to use generic device

#229 ffd000 opened 2 months ago
0
Second stage training with smaller window size

#228 meng2468 opened 2 months ago
1
SLM Adversarial Training did not start when finetuning

#227 godspirit00 opened 2 months ago
11
Better LJSpeech or LibriTTS for finetuning a single speaker voice? Or training from scratch with not so much data?

#226 Sweetapocalyps3 opened 2 months ago
3
Finetune on ljspeech or libritts?

#224 Weroxig closed 3 months ago
1
Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch

#223 ethan-digi opened 3 months ago
2
Very high GPU memory usage in voice cloning after 10-15 runs.

#222 amssss0 opened 3 months ago
1
Small bug in train_finetune

#220 Karesto opened 3 months ago
0
Simple clean ups

#219 astricks opened 3 months ago
2
Low GPU Utilization during training

#217 ayushtues opened 3 months ago
10
weird pulse at the end of the model

#216 matmult opened 3 months ago
3
StyleTTS2 Training for vietnamese

#215 Jedi92614 opened 3 months ago
0
Wrong kernel sizes in the JDC model

#214 Rifur13 opened 3 months ago
1
Did you add data beyond that of OOD_tests.txt ?

#212 CrossPr0duct opened 3 months ago
0
Update README.md

#209 yl4579 closed 3 months ago
2
self._shortcut(x) + self._residual(x) - The size of tensor a (34) must match the size of tensor b (35) at non-singleton dimension 2

#208 gooofy closed 3 months ago
4
Build a simple API interface

#207 MohannadEhabBarakat closed 3 months ago
11
error in first train gen loss=0.0

#206 lpscr opened 4 months ago
5
Train in one language and synthesize in English

#205 lucasgris closed 3 months ago
3
Same voice with different emotion

#203 enla51 closed 3 months ago
5
Voice Quality issue using Librispeech

#201 Anshu-Kumar-1 closed 3 months ago
1
Finetune duration_proj return NaN

#200 lIkesimba9 closed 3 months ago
2
Understanding Style tts training process

#198 SanketDhuri closed 4 months ago
1
Fine-tuning or training from scratch in a differente language?

#197 paulovasconcellos-hotmart opened 5 months ago
21