as-ideas/TransformerTTS

Issues

• [CONTRIBUTION] Speech Dataset Generator

  #149 opened a year ago by davidmartinrius
  0

• About model structute.

  #145 opened a year ago by sunnnnnnnny
  0

• how's the speed comparasion with tacotron2?

  #78 opened 4 years ago by lucasjinreal
  1

• DeepPhonemizer? (Phonemizer License Issue)

  #143 opened a year ago by fakerybakery
  0

• how Normalized dataset

  #142 opened 2 years ago by herokarimpoor
  0

• error to run a train_aligner.py

  #141 opened 2 years ago by herokarimpoor
  0

• Error : raise StopIteration StopIteration

  #140 opened 2 years ago by farhadrahimiinfo
  0

• Can't Finish PHONEMIZING On Google Colab.

  #139 opened 2 years ago by The-Sad-Zewalian
  2

• Alignments in PyTorch implementation

  #138 opened 2 years ago by alexvwegen
  0

• model.pt

  #136 opened 2 years ago by JJun-Guo
  0

• the missing of HiFiGAN model.pt

  #130 opened 3 years ago by chikiuso
  2

• Pause between sentence

  #131 opened 3 years ago by chikiuso
  0

• How to install on windows?

  #126 opened 3 years ago by VieM2k18
  0

• Other Languages - Indonesian

  #111 opened 3 years ago by danirisdiandita
  5

• Get rid of the "robotic" sound

  #121 opened 3 years ago by alexvwegen
  4

• No module named 'decorator'

  #124 opened 3 years ago by johndpope
  0

• model.hdf5 file does not create

  #122 opened 4 years ago by AyseEe501
  0

• layer.py TransposedCNNResNorm

  #118 opened 4 years ago by zxp54332
  0

• Word timestamps

  #117 opened 4 years ago by tylerweitzman
  0

• inference error

  #114 opened 4 years ago by sciai-ai
  1

• how can i save the audio file if i am using thee pretrained model in google colab

  #116 opened 4 years ago by baniyacoder
  0

• Training in 3090 takes ~30 seconds per step

  #112 opened 4 years ago by agonzalezd
  2

• ERROR: while preparing training data

  #113 opened 4 years ago by sciai-ai
  1

• The training process takes forever `python train_tts.py --config config/training_config.yaml`

  #110 opened 4 years ago by danirisdiandita
  1

• Error occurred when finalizing GeneratorDataset iterator: Failed precondition: Python interpreter state is not initialized. The process may be terminated.

  #97 opened 4 years ago by oyeamit
  4

• Errors with dependencies and Summary during aligner, duration_extraction and training

  #100 opened 4 years ago by prajwaljpj
  6

• No numbers in phonemes set and collapse of whitespaces

  #105 opened 4 years ago by anh
  2

• model cannot predict

  #80 opened 4 years ago by sciai-ai
  0

• Sequence level kD in fastspeech

  #99 opened 4 years ago by bkumardevan07
  1

• a activation function is missing in FFNResNorm.

  #102 opened 4 years ago by hccho2
  1

• Convergence of forward model

  #101 opened 4 years ago by bkumardevan07
  1

• Fine-tuning HifiGAN using output mels

  #92 opened 4 years ago by kudanai
  7

• ERROR during preprocessing

  #93 opened 4 years ago by luis-vera
  3

• While training using train_tts.py, the validation is weird.

  #98 opened 4 years ago by kampores
  3

• duration not predicted correctly

  #95 opened 4 years ago by theAayushbajaj
  1

• Regd Forcing Encoder Attention Alignments

  #96 opened 4 years ago by bkumardevan07
  1

• Where is train_tts.py?

  #94 opened 4 years ago by kampores
  1

• Why does GPU take up so much resources？

  #91 opened 4 years ago by gucasbrg
  1

• Does it support multi-gpu training?

  #88 opened 4 years ago by holdurhorses
  1

• how to convert Chinese to speech?

  #87 opened 4 years ago by xiakj
  0

• Regarding mel start and end token

  #72 opened 4 years ago by bkumardevan07
  7

• Query regarding Model architecture

  #81 opened 4 years ago by bkumardevan07
  1

• About reduction_factor_schedule

  #79 opened 4 years ago by taylorlu
  3

• The declaration of the'bucket_boundaries' variable in the data_handler.get_dataset() function is omitted, resulting in an error.

  #77 opened 4 years ago by kampores
  0

• Problemas with ## Prediction

  #76 opened 4 years ago by luis-vera
  1

• Why use dropout in decoder prenet also in inference?

  #75 opened 4 years ago by iclementine
  1

• All elements in a batch must have the same rank

  #74 opened 4 years ago by pourfard
  1

• Can voice control be used somehow to make generated audio sound like a particular voice?

  #73 opened 4 years ago by shamoons
  1

• extract_durations.py slowly filling up RAM and gets killed

  #69 opened 4 years ago by padmalcom
  2

• Shapes in forward model does not match

  #68 opened 4 years ago by mehdihosseinimoghadam
  3