jojojaeger/whisper-streamlit

Issues

• For better transcription in more languages, Implement Massively Multilingual Speech - Meta's Open Source model with less than half of Whispers error rate

  #4 opened a year ago by menelic
  2

• English Language

  #1 opened a year ago by ThatsMyCall
  4

• Speaker recognition tickbox option missing

  #6 opened a year ago by menelic
  5

• Transcription fails with TypeError: DecodingOptions.__init__() got an unexpected keyword argument 'word_timestamps' Traceback:

  #3 opened a year ago by menelic
  3

• Make transcript editable

  #8 opened a year ago by menelic
  0

• Make audio for transcribed segment playable by integraing play button next to the segment

  #7 opened a year ago by menelic
  0

• In Requirements.txt Streamlit must be set to streamlit==1.22.0 to avoid error

  #2 opened a year ago by menelic
  2