speechlib is a library that can do speaker diarization, transcription and speaker recognition on an audio file to create transcripts with actual speaker names
MIT License
138
stars
12
forks
source link
Add hhmmss or use audio file to form transcript file name. #9
Currently output file has only ymd (output_2024-01-22.txt), meaning each transcript run on same day overwrites the previous. Is this desired behaviour? Don't think so.
Currently output file has only ymd (output_2024-01-22.txt), meaning each transcript run on same day overwrites the previous. Is this desired behaviour? Don't think so.
transcript-2024-01-22-140515.txt will solve this
Or maybe use file name, example
audio_file > "DonaldTrumpSpeech2012.mp3"
transcript > "DonaldTrumpSpeech2012.txt"