bnosac/audio.whisper

Issues

• Transcipt segment size

  #66 opened 2 months ago by FlorianPrimig
  1

• upgrade to whisper.cpp 1.5.5

  #64 opened 7 months ago by jwijffels
  5

• Integrating audio.whisper and audio.vadsilero

  #62 opened 8 months ago by jmgirard
  9

• distil-whisper

  #63 opened 7 months ago by jwijffels
  0

• Notes on repetitions

  #38 opened 9 months ago by jwijffels
  4

• Integrate CUDA support

  #27 opened 8 months ago by jwijffels
  39

• Latest release

  #61 opened 8 months ago by jmgirard
  1

• add diarization output to token information

  #60 opened 8 months ago by jwijffels
  1

• integrate with audio.vadwebrtc

  #50 opened 8 months ago by jwijffels
  1

• Add diarization

  #28 opened 8 months ago by jwijffels
  2

• alternatives to provide binaries

  #54 opened 8 months ago by jwijffels
  5

• upgrade to 1.5.0

  #24 opened 10 months ago by jwijffels
  27

• Integrate CoreML

  #35 opened 10 months ago by jwijffels
  6

• Add examples on quantised models

  #31 opened 9 months ago by jwijffels
  0

• Integrate hipBLAS (AMD)

  #49 opened 9 months ago by jwijffels
  0

• Integrate OpenCL

  #48 opened 9 months ago by jwijffels
  0

• Integrate Metal

  #34 opened 9 months ago by jwijffels
  26

• Integrate OpenBlas

  #41 opened 9 months ago by jwijffels
  2

• Integrate OpenVINO

  #42 opened 9 months ago by jwijffels
  0

• Add initial prompt

  #39 opened 9 months ago by jwijffels
  0

• Add language detection

  #30 opened 10 months ago by jwijffels
  0

• List of compilation flags for audio.whisper up to 0.2.2 with whisper.cpp 1.2.1

  #15 opened 2 years ago by jwijffels
  4

• List of compilation flags for audio.whisper >= 0.3 with whisper.cpp 1.5.4

  #26 opened 10 months ago by jwijffels
  0

• Error when loading model

  #22 opened 10 months ago by azoezoe
  6

• put extra arguments in front end function

  #14 opened 10 months ago by jwijffels
  3

• R Crashes When Running the Model

  #23 opened a year ago by brownj31
  4

• Base model detects music whereas tiny detects lyrics?

  #17 opened a year ago by sebsilas
  2

• Problems with the version of audio.whisper

  #19 opened a year ago by SebastianPereyra
  6

• Error when trying to download model files

  #20 opened a year ago by jmgirard
  3

• URLs hard-coded in the model download package are incorrect

  #18 opened a year ago by prolabrus
  3

• Can't load models from small and above

  #16 opened a year ago by sebsilas
  7

• incorporate compilation improvements

  #8 opened 2 years ago by jwijffels
  7

• Transcript to French

  #11 opened 2 years ago by CharlyMarie
  3

• incorporate release 1.1.0

  #10 opened 2 years ago by jwijffels
  1

• incorporate release v1.2.1

  #13 opened 2 years ago by jwijffels
  1

• Unable to transcribe on Linux

  #12 opened 2 years ago by carlganz
  4

• set up unit tests

  #9 opened 2 years ago by jwijffels
  0

• fix all abort / exit / stderr / stdout statements

  #1 opened 2 years ago by jwijffels
  2

• improve makevars

  #4 opened 2 years ago by jwijffels
  3

• dr_libs

  #6 opened 2 years ago by jwijffels
  1

• move Files in src: whisper.cpp, whisper.h, ggml.c and ggml.h and main.cpp to whisper folder

  #3 opened 2 years ago by jwijffels
  1

• move model loading to whisper instead of predict.whisper

  #5 opened 2 years ago by jwijffels
  1

• return information at word level

  #2 opened 2 years ago by jwijffels
  0