speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts with actual speaker names
using faster-whisper==1.0.2
Adds MPS support for faster inferencing on Macs
changelog:
log file saved as filename_HHMMSS_language.txt
change log:
changed readme and library.md
added examples
changed a bit
added whisper tiny, large model support added preprocessor functions changed readme
fixed issues with files having different encoding and multiple channels.