Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / yl4579/StyleTTS2 issues and pull requests
#282 - (Q) Multi/Single Speaker different language finetune
Issue -
State: open - Opened by mantrakp04 16 days ago
- 6 comments
#281 - Training Curves
Issue -
State: open - Opened by atosystem 23 days ago
- 3 comments
#279 - What is the chinese phonemizer for pretrained multilinugual PL-BERT?
Issue -
State: open - Opened by YuXiangLin1234 about 1 month ago
#278 - [GARDENING]: Freeze package versions
Pull Request -
State: closed - Opened by pranav-vijayakumarrao-techlabs about 1 month ago
#277 - Wav File not being read
Issue -
State: closed - Opened by MARafey about 2 months ago
#276 - Fix weird pulse at the end of the model
Pull Request -
State: open - Opened by ZZDoog about 2 months ago
#275 - ImportError: A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.1
Issue -
State: closed - Opened by Geremia about 2 months ago
- 1 comment
#274 - Do we need lr scheduler?
Issue -
State: open - Opened by Dforgeek about 2 months ago
- 2 comments
#273 - 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]
Issue -
State: open - Opened by fungus75 about 2 months ago
- 1 comment
#272 - StyleTTS Python API doesn't detect devanagari script
Issue -
State: open - Opened by tanishbajaj101 2 months ago
#271 - Can StyleTTS2 use phonemization from different languages to finetune or train?
Issue -
State: open - Opened by tanishbajaj101 2 months ago
#270 - Model Size of fine tuned Model
Issue -
State: open - Opened by deguodedongxi 2 months ago
#269 - Refactored code for improved readability and performance
Pull Request -
State: open - Opened by zolero 2 months ago
#268 - Can anyone please share checkpoints that we get after we complete both stages of training
Issue -
State: open - Opened by tanishbajaj101 2 months ago
- 4 comments
#267 - Training PL-BERT on styletts2-community/multilingual-pl-bert
Issue -
State: open - Opened by kikozi2000 2 months ago
#265 - weird chinese pronunciation
Issue -
State: open - Opened by SaltedSlark 3 months ago
- 3 comments
#264 - Questions about Differentiable Duration Modeling
Issue -
State: open - Opened by RoversCode 3 months ago
- 1 comment
#263 - In 2nd stage training AttributeError: 'AudioDiffusionConditional' object has no attribute 'module'
Issue -
State: open - Opened by SandyPanda-MLDL 3 months ago
#262 - Joint training is failing with Assertion error
Issue -
State: open - Opened by nvadigauvce 3 months ago
- 2 comments
#261 - Can the model learn accents not supported by espeak-ng?
Issue -
State: open - Opened by nigh8w0lf 3 months ago
#260 - Getting error in d_loss.backward() of first_stage training
Issue -
State: open - Opened by SandyPanda-MLDL 3 months ago
#259 - First stage training after 49th epoch (i.e., when epoch >= TMA_epoch)
Issue -
State: open - Opened by SandyPanda-MLDL 3 months ago
#258 - In training Stage1 after 49th epoch getting RuntimeError: you can only change requires_grad flags of leaf variables, g_loss.requires_grad = True
Issue -
State: open - Opened by SandyPanda-MLDL 3 months ago
- 2 comments
#257 - Multi-lingual training
Issue -
State: open - Opened by nvadigauvce 3 months ago
- 29 comments
#256 - Getting CUDA Out of memory error in Stage2 training
Issue -
State: closed - Opened by SandyPanda-MLDL 3 months ago
- 15 comments
#254 - Stage 2 Training Fails with NaN Loss on Single GPU Due to Inconsistent Checkpoint Keys
Issue -
State: open - Opened by 5Hyeons 3 months ago
#253 - feat: Improve model checkpoint loading
Pull Request -
State: open - Opened by 5Hyeons 3 months ago
#252 - Error Message After Using a fine tuned ASR Model
Issue -
State: open - Opened by GUUser91 3 months ago
#249 - Test trt
Pull Request -
State: closed - Opened by siddhatiwari 3 months ago
#248 - FP8 Fine Tuning Crashes
Issue -
State: open - Opened by GUUser91 4 months ago
- 1 comment
#247 - Train finetune logging
Pull Request -
State: closed - Opened by zjaffal 4 months ago
#246 - Speech conditioning like tortoise TTS
Issue -
State: open - Opened by NikitaKononov 4 months ago
- 1 comment
#245 - Inference Error: context_features exists but no features provided
Issue -
State: closed - Opened by JeffryCA 4 months ago
- 1 comment
#244 - S_loss = 0 ... why?
Issue -
State: closed - Opened by DrBrule 4 months ago
- 2 comments
#243 - May be a bug? input parameters for model.predictor_encoder and model.style_encoder in train_finetune.py
Issue -
State: open - Opened by starmoon-1134 4 months ago
#242 - During training, the graphics memory has been continuously increasing
Issue -
State: open - Opened by Wentao795 4 months ago
- 1 comment
#240 - Inference with multilingual PL-BERT Model
Issue -
State: closed - Opened by deguodedongxi 4 months ago
- 4 comments
#239 - Help Wanted For Stage-1
Issue -
State: open - Opened by xujzouyyz 4 months ago
- 3 comments
#238 - Resuming finetuning uses second to last epoch
Issue -
State: open - Opened by SimonDemarty 4 months ago
- 1 comment
#237 - Code organization (train_first.py and related utils)
Pull Request -
State: closed - Opened by astricks 4 months ago
- 1 comment
#236 - asr negative loss
Issue -
State: open - Opened by yijingshihenxiule 5 months ago
- 1 comment
#235 - HELP WANTED!!!!!!!!!!!
Issue -
State: closed - Opened by 21sK1p 5 months ago
- 4 comments
#234 - Cannot Convert float NaN to integer
Issue -
State: closed - Opened by SimonDemarty 5 months ago
- 1 comment
#233 - Issue with impropper pauses and random bursts of noise
Issue -
State: open - Opened by king-dahmanus 5 months ago
- 1 comment
#230 - Possible Bug in Style Diffusion Inference Code
Issue -
State: closed - Opened by brthor 5 months ago
#229 - Update training scripts to use generic device
Pull Request -
State: open - Opened by ffd000 5 months ago
- 2 comments
#228 - Second stage training with smaller window size
Issue -
State: open - Opened by meng2468 5 months ago
- 2 comments
#227 - SLM Adversarial Training did not start when finetuning
Issue -
State: open - Opened by godspirit00 5 months ago
- 13 comments
#226 - Better LJSpeech or LibriTTS for finetuning a single speaker voice? Or training from scratch with not so much data?
Issue -
State: open - Opened by Sweetapocalyps3 6 months ago
- 4 comments
#224 - Finetune on ljspeech or libritts?
Issue -
State: closed - Opened by Weroxig 6 months ago
- 1 comment
#223 - Strange Loss Behavior During Stage Two Training - Not Decreasing after Diff Epoch
Issue -
State: open - Opened by ethan-digi 6 months ago
- 3 comments
#222 - Very high GPU memory usage in voice cloning after 10-15 runs.
Issue -
State: open - Opened by amssss0 6 months ago
- 2 comments
#220 - Small bug in train_finetune
Issue -
State: open - Opened by Karesto 6 months ago
- 2 comments
#219 - Simple clean ups
Pull Request -
State: open - Opened by astricks 6 months ago
- 2 comments
#217 - Low GPU Utilization during training
Issue -
State: open - Opened by ayushtues 6 months ago
- 10 comments
#216 - weird pulse at the end of the model
Issue -
State: open - Opened by matmult 6 months ago
- 5 comments
#215 - StyleTTS2 Training for vietnamese
Issue -
State: open - Opened by Jedi92614 6 months ago
- 1 comment
#214 - Wrong kernel sizes in the JDC model
Issue -
State: open - Opened by Rifur13 6 months ago
- 1 comment
#212 - Did you add data beyond that of OOD_tests.txt ?
Issue -
State: open - Opened by CrossPr0duct 7 months ago
#209 - Update README.md
Pull Request -
State: closed - Opened by yl4579 7 months ago
- 2 comments
#208 - 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
Issue -
State: closed - Opened by gooofy 7 months ago
- 4 comments
#207 - Build a simple API interface
Pull Request -
State: closed - Opened by MohannadEhabBarakat 7 months ago
- 11 comments
#206 - error in first train gen loss=0.0
Issue -
State: open - Opened by lpscr 7 months ago
- 6 comments
#205 - Train in one language and synthesize in English
Issue -
State: closed - Opened by lucasgris 7 months ago
- 3 comments
#203 - Same voice with different emotion
Issue -
State: closed - Opened by enla51 7 months ago
- 5 comments
#201 - Voice Quality issue using Librispeech
Issue -
State: closed - Opened by Anshu-Kumar-1 7 months ago
- 1 comment
#200 - Finetune duration_proj return NaN
Issue -
State: closed - Opened by lIkesimba9 7 months ago
- 2 comments
Labels: duplicate
#197 - Fine-tuning or training from scratch in a differente language?
Issue -
State: open - Opened by paulovasconcellos-hotmart 8 months ago
- 27 comments
Labels: help wanted
#195 - Add a gitignore file
Pull Request -
State: closed - Opened by astricks 8 months ago
#193 - train_second.py model.decoder error (output tensor is nan)
Issue -
State: open - Opened by junylee11 8 months ago
- 5 comments
#188 - Chinese data
Issue -
State: closed - Opened by russell-shu 8 months ago
- 4 comments
#187 - OOD data for LibriTTS-460 training?
Issue -
State: closed - Opened by kmn1024 8 months ago
- 1 comment
#186 - Training a Japanese model, pitch accent and IPA
Issue -
State: closed - Opened by NielsVandenEynde 9 months ago
- 1 comment
#178 - When start firtst_train give errors. I have 96 Gb Ram and 3 P40/24GB/ 1 T4 /16GB/ ??
Issue -
State: closed - Opened by casic 9 months ago
- 10 comments
#176 - 你好,请问模型支持流式tts吗?
Issue -
State: closed - Opened by bobo-paopao 9 months ago
- 1 comment
#175 - stage1 training issue
Issue -
State: closed - Opened by zhiqiuiyiye 9 months ago
- 6 comments
#174 - Speech-to-speech possible?
Issue -
State: closed - Opened by vbrydik 9 months ago
- 4 comments
#170 - An Error From LJspeech Dataset
Issue -
State: closed - Opened by YJCmote1 9 months ago
- 2 comments
#166 - Fix batch size 1 by specifying squeeze dims
Pull Request -
State: open - Opened by Sobsz 9 months ago
- 10 comments
#156 - Is It Possible to Get Word-Level Timestamps for Generated Audio?
Issue -
State: closed - Opened by jtschoonhoven 9 months ago
- 2 comments
#150 - how to generate a more diverse voice by preset a random latent style embedding?
Issue -
State: closed - Opened by blldd 9 months ago
- 2 comments
#147 - the size of tensor a (251) must match the size of tensor b (51) at non-singleton dimension 2
Issue -
State: closed - Opened by 11721206 9 months ago
- 4 comments
#139 - mandrain results sharing and training support
Issue -
State: closed - Opened by liuhuang31 10 months ago
- 15 comments
#132 - ValueError: a must be greater than 0 unless no samples are taken
Issue -
State: closed - Opened by bobo-paopao 10 months ago
- 6 comments
#126 - An error occurred suddenly during the fine-tuning process
Issue -
State: closed - Opened by 81549361 10 months ago
- 2 comments
#117 - Is it possible to make onnx model support?
Issue -
State: open - Opened by orkars 10 months ago
- 5 comments
Labels: help wanted
#114 - Mac (Metal) support?
Issue -
State: open - Opened by itsPreto 10 months ago
- 33 comments
Labels: help wanted
#112 - Bug during Second Stage Training
Issue -
State: closed - Opened by asusdisciple 10 months ago
- 3 comments
#106 - Support for batch inference
Issue -
State: closed - Opened by devidw 10 months ago
- 8 comments
#100 - Rough Accelerate implementation, and updated finetuning colab
Pull Request -
State: closed - Opened by korakoe 10 months ago
- 15 comments
#99 - Trying to fine tune with SLM adversarial training
Issue -
State: closed - Opened by jazza420 10 months ago
- 2 comments
#89 - h100: Worse output & 20x slower inference?
Issue -
State: open - Opened by addytheyoung 10 months ago
- 13 comments
Labels: help wanted
#62 - Phonemizer Replacement
Issue -
State: closed - Opened by fakerybakery 10 months ago
- 8 comments
#46 - Loud white noise on short texts with embedding_scale > 1
Issue -
State: open - Opened by AWAS666 10 months ago
- 18 comments
Labels: bug
#41 - Awesome in english but no support for other languages - please add an example for another language (german, italian, french etc)
Issue -
State: open - Opened by cmp-nct 10 months ago
- 83 comments
Labels: help wanted
#40 - Licensing issue
Issue -
State: closed - Opened by fakerybakery 10 months ago
- 10 comments
Labels: help wanted
#13 - High-pitched noise in the background when using old GPUs
Issue -
State: open - Opened by danielmsu 12 months ago
- 8 comments
Labels: bug
#11 - g_loss is None in second stage training
Issue -
State: closed - Opened by haoqi 12 months ago
- 20 comments
#8 - Multispeaker Config
Issue -
State: closed - Opened by bhairavmehta95 12 months ago
- 5 comments
#7 - Extremely weird DDP issue for train_second.py
Issue -
State: open - Opened by yl4579 12 months ago
- 30 comments
Labels: bug, help wanted