huggingface/distil-whisper

Issues

• Distil-Whisper model sometimes fails with "index x is out of bounds for dimension 0 with size y" error

  #148 opened a month ago by aleksandr-mokrov
  2

• How to load a fine-tuned model for inference？

  #145 opened 5 months ago by xinliu9451
  1

• Is there a way to run this on a browser?

  #157 opened 2 months ago by FerLuisxd
  0

• distil-whisper-turbo

  #154 opened 3 months ago by simpthy
  1

• Speculative Decoding: TypeError: list indices must be integers or slices, not tuple (Apple M1 MacOS Sonoma 14.6.1)

  #153 opened 3 months ago by solitaryangler
  0

• Repository Not Found for url

  #136 opened 7 months ago by wailokkwok
  3

• Using run distillation lead to a high .cache use

  #151 opened 3 months ago by Gusreis7
  0

• Using run_distillation.py code for fine-tuning the pretrained model

  #150 opened 3 months ago by Hannan-Komari
  0

• How to load using openai-whisper package to load the model?

  #149 opened 3 months ago by lucasjinreal
  0

• Trying to distil whisper for arabic Language but faced an error in step 3

  #147 opened 5 months ago by Manel-Hik
  0

• How many hours for the French version

  #146 opened 5 months ago by virtualmartire
  0

• Cannot continue training for custom dataset

  #144 opened 5 months ago by alicewith
  0

• The fine-tuning issue regarding this project

  #143 opened 5 months ago by lq0104
  0

• Unable to set concatenate_audio parameter to False in run_pseudo_labelling.py

  #133 opened 6 months ago by lq0104
  0

• Problems in concatenate_dataset

  #129 opened 6 months ago by George0828Zhang
  0

• ZeroDivisionError: division by zero

  #137 opened 7 months ago by wailokkwok
  0

• Discrepancy on WER benchmark result in Tedlium dataset

  #135 opened 7 months ago by GeeYangML
  1

• Unable to reproduce results from the paper

  #131 opened 7 months ago by GeeYangML
  6

• How to set the target language for examples in README?

  #130 opened 8 months ago by clstaudt
  7

• [Question] Can we distill for multiple langauges for distil-small-whisper

  #107 opened 9 months ago by Killshot667
  3

• Resuming training fails

  #105 opened 9 months ago by hidoba
  3

• question about when to apply WER threshold filtering strategy with concatenated audio

  #127 opened 8 months ago by lq0104
  0

• Finetuning on which model?

  #104 opened 9 months ago by RohitMidha23
  1

• Whisper-tiny support?

  #84 opened 10 months ago by alicewith
  2

• RuntimeError: User specified an unsupported autocast device_type 'mps'

  #119 opened 8 months ago by afsara-ben
  0

• perceptually faster inference through pre-completion inference of audio

  #114 opened 9 months ago by sujitvasanth
  0

• Quantize distil-whisper?

  #113 opened 9 months ago by sujitvasanth
  0

• Question: should the pseudo-labelling model and teacher model be the same?

  #92 opened 9 months ago by guynich
  2

• BetterTransformer optimization / flash_attn{_2}

  #93 opened 9 months ago by thomaschhh
  6

• How to use distil-whisper-large-v3-de-kd model from HF?

  #95 opened 10 months ago by Arche151
  10

• [Issue] latest run_pseudo_labelling.py

  #106 opened 9 months ago by ckcraig01
  0

• Training README datasets table: text column and id column

  #97 opened 9 months ago by guynich
  4

• WER Filtering takes too long?

  #80 opened a year ago by macabdul9
  3

• distil-small.en AttributeError

  #90 opened 9 months ago by andrewjones0198
  3

• Errors running `run_long_form_eval.py`

  #87 opened 9 months ago by guynich
  1

• Why do we need to tokenized file_id?

  #82 opened 9 months ago by macabdul9
  1

• large-v2 for english lost voice to text

  #100 opened 9 months ago by machenme
  1

• any executable script for running on custom data/given dataset

  #99 opened 9 months ago by afsara-ben
  1

• Voxpopuli text column "raw_text" HF dataset card shows empty string.

  #98 opened 9 months ago by guynich
  1

• Pseudo-labelling librispeech_asr (train.360): KeyError `train-360` when not streaming.

  #96 opened 9 months ago by guynich
  1

• Cached English Common Voice dataset size.

  #94 opened 10 months ago by guynich
  1

• transcription results are inconsistent and timestamps are None type. Issue appears in the latest version of the transformers==4.38.1.

  #91 opened 10 months ago by kranipa
  0

• Loss Weight ablation experiment

  #75 opened a year ago by JinYu1998
  3

• Cannot do pseudo-labelling due to some error

  #83 opened 10 months ago by alicewith
  2

• Best way to implement streaming application?

  #89 opened 10 months ago by 9throok
  0

• Short form evaluation WER % for Librispeech clean test

  #88 opened 10 months ago by guynich
  3

• Training README triggers BuildConfig ValueError

  #86 opened 10 months ago by guynich
  3

• Avoid preprocessing dataset again?

  #78 opened a year ago by marianbastiUNRN
  1

• I want to confirm how the knowledge organization is implemented？

  #73 opened a year ago by hxypqr
  1

• Is there the "distil-whisper/distil-medium" model?

  #72 opened a year ago by bk111
  1