as-ideas/DeepPhonemizer

Issues

• Is There a Sample Showing How to Convert to ONNX?

  #41 opened a year ago by SeymourNickelson
  8

• Quick question: where do the pretrained model's phoneme dictionaries come from?

  #33 opened 2 years ago by ADD-eNavarro
  3

• Need instructions for porting the trained model to tflite via onnx

  #23 opened 2 years ago by kafan1986
  8

• Convert to model

  #45 opened 6 months ago by NextDevX
  1

• Fine-tune existing model

  #44 opened 7 months ago by fakerybakery
  0

• latin_ipa_forward set to en_us pronounces "is" as "aɪz" rather than "ɪz"

  #35 opened 2 years ago by R2D2FISH
  1

• Numeric values in sentences not being Phonemized

  #43 opened a year ago by SeymourNickelson
  0

• Auto-Download + Load Checkpoints?

  #39 opened a year ago by fakerybakery
  3

• latin_ipa_forward checkpoint dropping german letter 'ß'

  #40 opened a year ago by stlohrey
  0

• Train sentences

  #16 opened 3 years ago by Frank995
  2

• New version does not save checkpoints properly

  #36 opened a year ago by thelahunginjeet
  1

• Modifying to generate multiple predictions

  #38 opened a year ago by netinupur
  0

• Checkpoint not working for multiple languages

  #37 opened a year ago by kafan1986
  0

• CMU Dictionary IPA Train/Test Dataset

  #34 opened 2 years ago by w11wo
  0

• `dp.utils` logging config is overriding app logging

  #25 opened 2 years ago by moritzhaller
  6

• Optimizer is None when trying to finetune a pretrained model

  #28 opened 2 years ago by inigo-casanueva
  1

• No delimiter in predictions from multi-letter phoneme codes

  #26 opened 2 years ago by thelahunginjeet
  1

• I am a newbi, I have a pretty simple question.

  #24 opened 2 years ago by xrick
  0

• Question about grapheme set

  #14 opened 3 years ago by kkp15
  11

• some character sets don't work

  #22 opened 2 years ago by hammondm
  7

• Transformer unable to predict double phonemes

  #20 opened 3 years ago by Frank995
  4

• Heteronym problem

  #21 opened 2 years ago by EdwinYam
  2

• training for Persian

  #19 opened 3 years ago by MahdiEsrafili
  2

• Question on overfitting

  #18 opened 3 years ago by Contextualist
  2

• Removing punctutation not working

  #17 opened 3 years ago by NickSmyr
  0

• Include stresses preidction

  #13 opened 3 years ago by stasbel
  4

• [BUG] On Windows 10 "preprocessor.phoneme_tokenizer" not output token id which is greater than 28

  #12 opened 3 years ago by ttklm20
  1

• some convert is not smart ,is there any configure to set?

  #10 opened 3 years ago by l2009312042
  2

• Problem exporting with JIT

  #11 opened 3 years ago by iggygeek
  2

• Issue while converting model using JIT script

  #9 opened 3 years ago by prajwaljpj
  3

• checkpoint: en_us_cmudict_forward

  #8 opened 3 years ago by staehlmich
  1

• ZeroDivisionError with run_training.py

  #2 opened 3 years ago by mbarnig
  4