fatchord/WaveRNN

Issues

• [CONTRIBUTION] Speech Dataset Generator

  #252 opened 9 months ago by davidmartinrius
  0

• Failed to build wheel for llvmlite

  #251 opened a year ago by adeel-afzaal
  0

• ModuleNotFoundError: No module named 'numba.decorators' When Running quick_start.py

  #250 opened a year ago by SamuelEnzi
  2

• (Solved, but can be useful to someone) Problems getting the project working for the first time

  #245 opened a year ago by forestrf
  0

• Is it possible to generate music using WaveRNN?

  #249 opened a year ago by gauripravishi
  0

• Help

  #248 opened a year ago by magicse
  0

• spectrogram (image_-to-wav

  #247 opened 2 years ago by ahmeftah
  1

• AttributeError: module 'librosa' has no attribute 'output'

  #239 opened 3 years ago by ljy-002
  4

• Where is the audio file for which itis generating the text?

  #244 opened 3 years ago by ayush431
  2

• Tacotron to Onnx

  #243 opened 3 years ago by manuel3265
  1

• python preprocess.py error

  #211 opened 4 years ago by LetsPlayPong
  5

• [feature request] dynamic batch size during WaveRNN training depending on free/total GPU memory

  #242 opened 3 years ago by Dmeerev
  0

• ValueError - gen_tacotron.py

  #234 opened 3 years ago by wierzs
  1

• data\\dataset.pkl isssue

  #241 opened 3 years ago by XSXIEYCH
  1

• why do you minus 2 in preprocessing ?

  #237 opened 3 years ago by yt605155624
  0

• adding support for windows sapi5

  #236 opened 3 years ago by king-dahmanus
  0

• Error During Computing Consensus Step

  #235 opened 3 years ago by rybioinf
  1

• Attention Blank, is it because my progressive training schedule?

  #223 opened 4 years ago by lilmadman007
  4

• Pre-trained models.

  #209 opened 4 years ago by anjanakethineni
  2

• Train WaveRnn AttributeError

  #233 opened 4 years ago by wierzs
  5

• sentence long problem

  #232 opened 4 years ago by sangiindalai
  0

• Can I use pretrained models with different hparams settings?

  #231 opened 4 years ago
  0

• Using wavernn pretrained model, loss stuck at 5.6

  #230 opened 4 years ago
  0

• Slow tacotron training 1step/sec on AWS p3.2xlarge (Tesla V100)

  #228 opened 4 years ago by ScottyBauer
  1

• Infinite loop during create_training_data.py

  #227 opened 4 years ago by luis-vera
  0

• How to split mel-spectrum in Multi-band wavernn?

  #219 opened 4 years ago by Shijie-Liu007
  2

• TTS not generating output even after 900k steps of tacotron model

  #226 opened 4 years ago by greatforu
  4

• Synthesized audio has noise

  #196 opened 5 years ago by MuyangDu
  10

• RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)

  #224 opened 4 years ago by theAayushbajaj
  0

• Some files are not being generated using "force_gta" parameter

  #200 opened 5 years ago by titospadini
  1

• librosa.util.exceptions.ParameterError: Audio buffer is not finite everywhere

  #225 opened 4 years ago by greatforu
  0

• How many clips to make a model?

  #222 opened 4 years ago by RM-urb
  0

• How to train better？

  #194 opened 5 years ago by 1zxLi
  3

• Tried to preprocess a custom dataset but it gave me error

  #218 opened 4 years ago by WellImDumb
  1

• Validation loss for tacotron?

  #221 opened 4 years ago by serg06
  0

• train_tacotron.py: Random CUBLAS_STATUS_INTERNAL_ERROR

  #216 opened 4 years ago by serg06
  5

• Converting generated MEL spectrograms to Tacotron 2 format, in order to use a different vocoder?

  #217 opened 4 years ago by serg06
  0

• train_wavernn.py CUDNN_STATUS_EXECUTION_FAILED on Windows 10 + CUDA 11 + cuDNN 8.0.4

  #215 opened 4 years ago by serg06
  1

• Description of the fatchord_version wavernn

  #212 opened 4 years ago by wsstriving
  2

• train tacotron error

  #207 opened 4 years ago by cycycy-g
  7

• How fast should training be? Getting 2.3 steps/s on RTX 3080

  #214 opened 4 years ago by serg06
  1

• Tensor CPU issue

  #201 opened 4 years ago by ayunus22198
  3

• AttributeError: Can't pickle local object 'get_tts_datasets.<locals>.<lambda>'

  #204 opened 4 years ago by Pritzier
  2

• train_tacotron.py giving error.

  #206 opened 4 years ago by anjanakethineni
  3

• Modifications for large number of utterances and reducing data size

  #205 opened 4 years ago by patrickltobing
  0

• train_tacotron.py not recognizing .csv file

  #202 opened 4 years ago by IamarockIamanisland
  1

• Preprocessing mels -- ran out of space

  #203 opened 4 years ago by taylerpauls
  0

• What about Tensorboard?

  #199 opened 5 years ago by titospadini
  0

• How do I understand the meaning of 1D Resnet and Upsampling?

  #198 opened 5 years ago by linzihyuan
  0

• Latest optimizer state for pretrained models

  #195 opened 5 years ago by lenbrocki
  0