Harras3/unhallucinated-faster-whisper
'unhallucinated-faster-whisper,' a powerful enhancement built on the faster-whisper framework for audio transcription.
This tool helps anyone who needs accurate text from audio recordings like interviews, podcasts, or meeting minutes. It takes your audio files and produces a reliable, written transcript, minimizing errors where the AI might otherwise make up words or phrases. Journalists, content creators, researchers, and administrative staff will find this particularly useful.
No commits in the last 6 months.
Use this if you need highly accurate, clean transcripts from audio, especially when minor inaccuracies would be problematic.
Not ideal if you just need rough, quick transcriptions and don't mind occasional made-up words, or if you're not working with audio files.
Stars
12
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Harras3/unhallucinated-faster-whisper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
Kieirra/murmure
Fully local, private and cross platform Speech-to-Text with LLM Post-processing
Softcatala/whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
pavelzbornik/whisperX-FastAPI
FastAPI service on top of WhisperX
royshil/obs-localvocal
OBS plugin for local speech recognition and captioning using AI