Re:Show HN: Python Audio Transcription: Convert Speech to Te...
by drewbuschhorn on Monday September 22, 2025 @03:04PM
(#45337977)
You should throw in some diarization, there's some pretty effective libraries that don't need pertraining on the voice separation in python.
[ Parent
| on HN ]
Re:Show HN: Python Audio Transcription: Convert Speech to Te...
by Pavlinbg on Monday September 22, 2025 @03:09PM
(#45338045)
Nice suggestion, I'll look them up.
Re:Show HN: Python Audio Transcription: Convert Speech to Te...
by nvdnadj92 on Monday September 22, 2025 @04:28PM
(#45339017)
I would suggest 2 speaker-diarization libraries:
- https://huggingface.co/pyannote/speaker-diarization-3.1 - https://github.com/narcotic-sh/senko
I personally love senko since it can run in seconds, whereas py-annote took hours, but there is a 10% WER (word error rate) that is tough to get around.