Gadersd/whisper-burn

Issues

• Trouble importing finetuned HuggingFace model

  #14 opened a year ago by AlienKevin
  13

• Use Burn's PyTorchFileRecoder to Directly Load PyTorch Model

  #25 opened 8 months ago by antimora
  0

• When using repo as library, incorrect version of burn gets used, adding version tag to cargo.toml may fix

  #23 opened 9 months ago by SamuelKurtzer
  0

• Assistance with creating a French configuration for whisper-burn

  #22 opened 10 months ago by Melfos-md
  0

• FR: sorta. Consider splitting out speech preprocessing into a separate crate

  #20 opened a year ago by skewballfox
  0

• WGPU issues in Macbook M1

  #19 opened a year ago by DavidGOrtega
  5

• Tinygrad dependancy for weights conversion

  #16 opened a year ago by DavidGOrtega
  1

• Python issues

  #17 opened a year ago by DavidGOrtega
  1

• Trying the example I got an empty transcription

  #15 opened a year ago by DavidGOrtega
  12

• Tinygrad import path changed in model conversion script

  #13 opened a year ago by AlienKevin
  1

• Garbage output on multi channel audio and audio above 24khz

  #9 opened a year ago by Quackdoc
  4

• Does using wgpu backend requires Torch to be installed?

  #11 opened a year ago by tiero
  1

• No output with 8 second clip?

  #4 opened a year ago by n8henrie
  3

• Muffled Text - Response for Custom Audio

  #10 opened a year ago by coderaidershaun
  1

• Changes to run on CUDA with TchBackend

  #8 opened a year ago by jbrough
  4

• Can not choose second gpu using wgpu

  #7 opened a year ago by Quackdoc
  2

• Transriptions fails using large-v2 model

  #6 opened a year ago by xelibrion
  1

• Panic while transcribing audio.wav

  #5 opened a year ago by meowcoder
  1

• bug: transcribing with medium model

  #2 opened a year ago by b0xtch
  4

• FR: Mention need for setting runtime paths for libtorch

  #1 opened a year ago by n8henrie
  8

• run by example encounted failure

  #3 opened a year ago by phlamenco
  1