Vaibhavs10/insanely-fast-whisper

Issues

• Diarization is very slow

  #224 opened 19 days ago by prkumar112451
  1

• "No module named wheel" when adding flash-attn on Windows

  #226 opened 14 days ago by jenny923432
  0

• Getting `Use model.to('Cuda')` when trying to use Flash Attention

  #210 opened a month ago by eburgwedel
  1

• `The operator 'aten::isin.Tensor_Tensor_out' is not currently implemented for the MPS device.` while running on macOS

  #225 opened 18 days ago by paulz
  0

• NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out'

  #219 opened a month ago by cyrilzakka
  2

• Get nearly double the performance gap with another docker image on the same system.

  #222 opened 23 days ago by lordofriver
  0

• [Question] Usage for consumer hardware?

  #221 opened 23 days ago by Yasand123
  0

• Torch not compiled with CUDA enabled

  #220 opened 23 days ago by welldawell
  0

• Error for Multiple languages audio

  #197 opened 2 months ago by SaddamBInSyed
  1

• { Feature request} Turn off Progress bar so it can run in batch.

  #218 opened a month ago by trobinson03195
  0

• pipx install insanely-fast-whisper outdated version

  #213 opened a month ago by LaansDole
  2

• where does insanely-fast-whisper store the downloaded model file?

  #217 opened a month ago by yinwei168
  0

• python inference code not different from "normal" whipser?

  #216 opened a month ago by wincing2
  0

• Out Of memory & attempt to get argmin of an empty sequence

  #199 opened 2 months ago by learner0333
  2

• Can I add - initial_prompt like whisper

  #207 opened 2 months ago by lvjin521
  1

• [Error] metadata-generation failed while trying to install flash-attention on google collab T4

  #215 opened a month ago by MahdeenSky
  0

• Local file

  #214 opened a month ago by kamalkech
  0

• Timestamps are too tight when repetition_penalty is present

  #208 opened 2 months ago by Brodski
  1

• Could we talk in discord mp about subtitles

  #212 opened a month ago by SpeederSpeederSpeder
  0

• Cuda Index Out of Bound error on GPU

  #211 opened a month ago by weichunnn
  0

• question: client sdk

  #209 opened 2 months ago by Tyrese-FullStackGenius
  0

• The speed is slower than fast-whisper, is something wrong in my config?

  #202 opened 2 months ago by Green-li
  1

• MPS flash attention support

  #206 opened 2 months ago by dreampuf
  0

• Doesn't detect CUDA

  #183 opened 3 months ago by dgoryeo
  3

• Speaker Diarization

  #205 opened 2 months ago by Yonahfireman
  0

• Using with replicate.com

  #204 opened 2 months ago by jjones3535a
  0

• What is the trade off in accuracy from fp32 to fp16

  #200 opened 2 months ago by KeystoneScience
  0

• Тема

  #195 opened 2 months ago by DaniilBornosuz
  0

• How is the accuracy and memory usage as compared to Faster Whisper?

  #167 opened 5 months ago by bakermanbrian
  2

• question on how this works?

  #196 opened 3 months ago by silvacarl2
  2

• num-speakers not yet available for pipx installed package

  #188 opened 3 months ago by skol101
  1

• Random and inconsistent transcribe

  #175 opened 3 months ago by Auth0rM0rgan
  4

• Is there a way to cap the max length of the transcription?

  #194 opened 3 months ago by wtlow003
  0

• Use as python lib and release format.

  #184 opened 3 months ago by jzju
  1

• [FEATURE REQUEST] support audio input from microphones

  #193 opened 3 months ago by RonnyPfannschmidt
  0

• Too high vRAM usage

  #191 opened 3 months ago by Majdoddin
  0

• is_flash_attn_2_available() returns False

  #192 opened 3 months ago by Majdoddin
  0

• api in replicate.com throws Prediction failed. invalid load key, '\x00'. error randomly

  #189 opened 3 months ago by bharatMW
  0

• I run code in colab and output comes with terms like ''{"speakers": [], "chunks": [{"timestamp": [0.0, 130.4]'' I would like to transcribe only the text - Is this possible ? How?

  #187 opened 3 months ago by maria88hds
  1

• How about some honest speed/quality tests for a change

  #186 opened 3 months ago by BBC-Esq
  0

• Can insanely-fast-whisper support real-time transcription with websockets?

  #185 opened 3 months ago by joaogabrieljunq
  0

• Missing 0.0.13 on pipx?

  #182 opened 3 months ago by jacksteamdev
  1

• torch_dtype only for torch.float16？

  #178 opened 4 months ago by yumianhuli1
  0

• FFMPEG is installed but it gives error showing its not.

  #177 opened 4 months ago by Brob3r
  1

• CLI Feature requests: 1) Output .srt files, 2) Sequentially process all audio files in directory

  #174 opened 4 months ago by ch826
  1

• pipx install fails on Mac OS Sonoma

  #172 opened 4 months ago by boxabirds
  3

• 언어를 변경 할 수 있나요?

  #173 opened 4 months ago by souk0721
  1

• Word Timestamps

  #171 opened 4 months ago by Matheusadler
  0

• Issue on macOS Ventura - ProductVersion: 13.6.3 - BuildVersion: 22G436?

  #165 opened 5 months ago by yvervoort
  2

• Is there an api to get the transcription progress？

  #168 opened 5 months ago by yumianhuli1
  0