r9y9/deepvoice3_pytorch

Issues

• train.py problem

  #227 opened 3 years ago by rabbia970
  2

• [CONTRIBUTION] Speech Dataset Generator

  #234 opened 9 months ago by davidmartinrius
  0

• Unknown hyperparameter type for use_preset

  #222 opened 4 years ago by rishabh004-ai
  2

• 'SinusoidalEncoding' object has no attribute '_backend'

  #228 opened 3 years ago by B1uee
  1

• Error when run train.py

  #198 opened 5 years ago by ccuiyuhan
  2

• Google Colab (TF 2.0)

  #196 opened 5 years ago by biligunb
  3

• Training issues

  #200 opened 2 years ago by ilyalasy
  0

• Both Sample Colab Notebooks No Longer Work

  #229 opened 3 years ago by windowshopr
  2

• Installation nightmare

  #226 opened 3 years ago by skol101
  0

• Deep voice 3 multi speaker on Colab - failed building wheel for lws

  #221 opened 4 years ago by mdkberry
  1

• Error while loading the model

  #219 opened 4 years ago by Parvez2017
  1

• n_vocab AttributeError

  #225 opened 3 years ago by SODAsoo07
  0

• voice tone

  #224 opened 3 years ago by luantunez
  0

• Dataset not available at link

  #223 opened 4 years ago by msaadqureshi
  0

• Huge qualitative difference between training time synthesize and Custom text synthesize

  #188 opened 5 years ago by Arafat4341
  1

• the result obtained by eval_model or synthesis is much worse than which is obtained by train process

  #201 opened 4 years ago by Eleanor456
  8

• Deep voice multi-speaker on Colab has pip install torch==0.3.1 error

  #220 opened 4 years ago by mdkberry
  0

• DeepVoice3 multi-speaker TTS en demo.ipynb fixes

  #217 opened 4 years ago by CaptainStabs
  2

• Problem with lws package

  #218 opened 4 years ago by Parvez2017
  2

• Using deprecated Tensorflow 1.

  #213 opened 4 years ago by nspeer12
  1

• pre trained model works but goes crazy on some sentences which are a bit long

  #216 opened 4 years ago by Tetsujinfr
  0

• About audio parameters settings

  #215 opened 4 years ago by QUTGXX
  0

• Samples cutting out early

  #212 opened 4 years ago by deepglugs
  0

• Slow down speaking rate?

  #211 opened 4 years ago by angoodkind
  0

• Key for all speaker_id's

  #210 opened 4 years ago by angoodkind
  0

• When synthesis waveform , why using linear-spec rather than mel-spec?

  #207 opened 4 years ago by ymzlygw
  1

• How to use other Vocoder to synthesis waveform?

  #209 opened 4 years ago by ymzlygw
  0

• Not Working for JSTU data?

  #206 opened 4 years ago by ymzlygw
  0

• size mismatch for seq2seq.encoder.embed_tokens.weight

  #208 opened 4 years ago by CathyW77
  2

• "ValueError: too many values to unpack (expected 2)" on training.py

  #205 opened 4 years ago by ymzlygw
  0

• Can i ask a question about multi speaker tts?

  #204 opened 4 years ago by sbkim052
  0

• Speaker adaption, size mismatch

  #203 opened 4 years ago by deeepgandhi
  0

• Speaker Adaptation

  #202 opened 4 years ago by deeepgandhi
  0

• Removed

  #199 opened 5 years ago by egaebel
  0

• Training Multi-Speaker Model on vctk got bad results!

  #197 opened 5 years ago by the-final
  0

• Noisy utterances for single words audio generation

  #195 opened 5 years ago by kapoorparul
  0

• Generating audios for more than 108 speakers?

  #193 opened 5 years ago by kapoorparul
  1

• What is the latest known pytorch version to train for speaker adaptation on Windows10?

  #194 opened 5 years ago by RaghothamRao
  1

• Two problem about reducing needed memory in training

  #192 opened 5 years ago by YihuaLiang95
  0

• Can I only use deepvoice3 to learn dataset embeddings?

  #191 opened 5 years ago by george-roussos
  0

• Increasing Training steps

  #190 opened 5 years ago by Arafat4341
  2

• Checkpoint steps

  #187 opened 5 years ago by Arafat4341
  0

• JSON data for Japanese Text

  #189 opened 5 years ago by Arafat4341
  0

• Problems with "present" parameter while working with JSUT

  #185 opened 5 years ago by Arafat4341
  2

• Resume training from previously saved checkpoint

  #186 opened 5 years ago by Arafat4341
  1

• Size mismatch for seq2seq.encoder.embed_tokens.weight

  #184 opened 5 years ago by Arafat4341
  4

• 'train.txt' is not generating in output directory after pre-processing

  #183 opened 5 years ago by Arafat4341
  2

• No module named version

  #180 opened 5 years ago by mahmoodn
  1

• Can't fine model checkpoints

  #182 opened 5 years ago by Arafat4341
  5

• Couldn't build proto file into descriptor pool!

  #181 opened 5 years ago by Arafat4341
  0