keithito/tacotron

Issues

• unable to run requirement.txt command

  #371 opened 3 years ago by A-d-DASARE
  2

• Tacotron with other vocoder

  #368 opened 2 years ago by huutuongtu
  0

• Error Installing MatPlotLib at 2.0.2

  #364 opened 4 years ago by Lucien950
  2

• How to set epoch ?

  #330 opened 5 years ago by mightmay
  2

• Freezing the model for deployment

  #370 opened 3 years ago by gautam247gk
  0

• Curious - modifying code to utilise more modern version of CUDA

  #366 opened 4 years ago by phil-fw60
  0

• Emotional speech synthesis

  #365 opened 4 years ago by luantunez
  5

• Missing dependencies

  #355 opened 4 years ago by HusseinYusufali
  4

• No alignment after 800 epochs when training from scratch / cold-start

  #362 opened 4 years ago by pmunaretto
  0

• Why we use audio samples as input in this code. Research paper stated that text sequence is the input to tacotron-2 model

  #361 opened 4 years ago by tanu456
  1

• No module named 'hparams'

  #333 opened 5 years ago by Hashirkhan1996
  6

• Cannot convert a symbolic Tensor Error

  #359 opened 4 years ago by thegeekywanderer
  2

• Checkpoint to TFlite conversion

  #358 opened 4 years ago by berkaycinci
  1

• Only noise in checkpoint audio.

  #354 opened 4 years ago by marshoepial
  3

• How can I call tacotron models in another python program

  #320 opened 4 years ago by z404
  1

• Resume Training using a checkpoint?

  #357 opened 4 years ago by berkaycinci
  2

• Tacotron2 for low resources languages

  #356 opened 4 years ago by YousafKhan1
  1

• Poor Alignment for 2 hours of audio over 500 epochs/ batch size 32

  #352 opened 4 years ago by BenAAndrew
  0

• deploy model on tensorflow serving

  #353 opened 4 years ago by dimanshu
  0

• start training from a checkpoint

  #325 opened 4 years ago
  4

• What is the minimum amount of memory we can use to train?

  #351 opened 4 years ago by aminbaig
  0

• Dataset Urdu

  #323 opened 5 years ago by tayyabvohra
  1

• Tensorflow GPU version Problem

  #313 opened 5 years ago by Prithwiraj12
  0

• Numpy errors

  #350 opened 4 years ago by dheera
  0

• Question: is it possible to use 2 GPUs to train the model faster?

  #349 opened 4 years ago by aminbaig
  0

• Number conversion issue

  #348 opened 4 years ago by francochen1987
  0

• data preprocess error

  #347 opened 4 years ago by expresschen
  1

• robotic voice

  #346 opened 5 years ago by Ashbajawed
  0

• output audio lenght

  #343 opened 5 years ago by Ashbajawed
  0

• training/train.txt'

  #342 opened 5 years ago by AyaLahlou
  3

• local host

  #322 opened 5 years ago
  1

• suggestions

  #340 opened 5 years ago by marshonhuckleberry
  0

• train

  #341 opened 5 years ago by marshonhuckleberry
  0

• requirements? (os,python)

  #338 opened 5 years ago by marshonhuckleberry
  1

• how to synthesize without browser interface?

  #339 opened 5 years ago by marshonhuckleberry
  1

• AttributeError: module 'numpy' has no attribute 'gcd'

  #337 opened 5 years ago by ohdan10
  0

• Configuration issues on Window

  #336 opened 5 years ago by sameedkhan123
  1

• Confused about how to specify max mel_frames in the output spectrogram and training audio sample length in hparams.py

  #335 opened 5 years ago by jjoe1
  0

• which parameter defines the max char length in the input text?

  #334 opened 5 years ago by jjoe1
  0

• dependency hell

  #329 opened 5 years ago by antonkulaga
  1

• Certain character isn't "learn", it is ignore

  #331 opened 5 years ago by LauraLQ
  0

• How do tacotron partition training set and test set?

  #328 opened 5 years ago by AeolusZane
  1

• Loss Exploded at 115000'th step and the output waves evaluated by the latest checkpoints are unintelligible.

  #327 opened 5 years ago by yilmazay74
  0

• Repetition at end of synthesised wavs

  #326 opened 5 years ago by fathimad11
  3

• The result of different "outputs_per_step" in hparam.py

  #318 opened 5 years ago by AppalachianWine
  0

• can anyone tell me how to deploy this on TensorFlow serving?

  #319 opened 5 years ago by dimanshu
  2

• How to synthesize 8-bit audio？

  #321 opened 5 years ago by AppalachianWine
  0

• Cuda toolkit problem in google colab

  #317 opened 5 years ago by al-faiyad
  0

• is it possible rewrite in golang and run on cpu?

  #316 opened 5 years ago by peter05010402
  0

• Audio generated using eval is not same as generated by demo_server for the same checkpoint

  #314 opened 5 years ago by prateekgupta891
  1