Pinned issues
Issues
- 22
Multi-lingual training
#257 opened by nvadigauvce - 6
error in first train gen loss=0.0
#206 opened by lpscr - 0
- 2
- 1
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 by SandyPanda-MLDL - 3
Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch
#223 opened by ethan-digi - 0
Wav File not being read
#277 opened by MARafey - 1
ImportError: A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.1
#275 opened by Geremia - 0
Do we need lr scheduler?
#274 opened by Dforgeek - 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 by fungus75 - 0
- 0
Can StyleTTS2 use phonemization from different languages to finetune or train?
#271 opened by tanishbajaj101 - 3
Can anyone please share checkpoints that we get after we complete both stages of training
#268 opened by tanishbajaj101 - 0
Model Size of fine tuned Model
#270 opened by deguodedongxi - 4
weird pulse at the end of the model
#216 opened by matmult - 13
- 3
weird chinese pronunciation
#265 opened by SaltedSlark - 0
- 0
Possible Bug in Style Diffusion Inference Code
#230 opened by brthor - 1
Questions about Differentiable Duration Modeling
#264 opened by RoversCode - 0
In 2nd stage training AttributeError: 'AudioDiffusionConditional' object has no attribute 'module'
#263 opened by SandyPanda-MLDL - 0
Joint training is failing with Assertion error
#262 opened by nvadigauvce - 0
- 0
- 0
- 2
Help Wanted For Stage-1
#239 opened by xujzouyyz - 13
- 2
S_loss = 0 ... why?
#244 opened by DrBrule - 0
Stage 2 Training Fails with NaN Loss on Single GPU Due to Inconsistent Checkpoint Keys
#254 opened by 5Hyeons - 0
Error Message After Using a fine tuned ASR Model
#252 opened by GUUser91 - 1
FP8 Fine Tuning Crashes
#248 opened by GUUser91 - 1
- 1
Speech conditioning like tortoise TTS
#246 opened by NikitaKononov - 0
May be a bug? input parameters for model.predictor_encoder and model.style_encoder in train_finetune.py
#243 opened by starmoon-1134 - 0
- 4
Inference with multilingual PL-BERT Model
#240 opened by deguodedongxi - 3
Better LJSpeech or LibriTTS for finetuning a single speaker voice? Or training from scratch with not so much data?
#226 opened by Sweetapocalyps3 - 0
Resuming finetuning uses second to last epoch
#238 opened by SimonDemarty - 3
HELP WANTED!!!!!!!!!!!
#235 opened by 21sK1p - 1
Cannot Convert float NaN to integer
#234 opened by SimonDemarty - 0
asr negative loss
#236 opened by yijingshihenxiule - 0
- 1
Second stage training with smaller window size
#228 opened by meng2468 - 10
Low GPU Utilization during training
#217 opened by ayushtues - 1
Finetune on ljspeech or libritts?
#224 opened by Weroxig - 0
Small bug in train_finetune
#220 opened by Karesto - 4
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 opened by gooofy - 0
StyleTTS2 Training for vietnamese
#215 opened by Jedi92614 - 1
Wrong kernel sizes in the JDC model
#214 opened by Rifur13 - 0
Did you add data beyond that of OOD_tests.txt ?
#212 opened by CrossPr0duct