Whisper large-v3
OpenAI · Sorti nov. 2023
Whisper large-v3 is OpenAI's open-weight, Apache 2.0 speech recognition model (1.55B parameters, 99 languages), which OpenAI says cuts errors 10 to 20% against large-v2. Run through faster-whisper in float16 on CUDA, it worked in our runs as a reliable per-line judge of sung vocals on a 6 GB GPU. Recommended for local transcription and checking, with two caveats: fast rap needs short windows, and it can misread words as profanity, so listen to flagged lines.
Est-ce fait pour vous ?
Recommandé pour
- Local, free transcription in 99 languages under the Apache 2.0 license, with no per-minute bill
- Checking generated vocals line by line against a lyric sheet: in our runs it scored every take per line, and the best-scoring take sang each line of a written jingle right
- Faster runs through faster-whisper, which its authors say is up to 4 times faster than the reference implementation at the same accuracy
- A 6 GB NVIDIA GPU: float16 on CUDA ran in our tests on an RTX 3060 Laptop GPU
Déconseillé pour
- Long, fast rap transcribed in one pass: it dropped the opening seconds in our runs; transcribe 5-second windows snapped to silence instead
- Publishing on its word alone: it misheard clean lyrics as profanity in our runs, so listen to every flagged line
- Speaker labels or live streaming captions out of the box; it is a batch transcriber without diarization
Tarifs
Entrée
Free (self-hosted open weights)
Sortie
Free (self-hosted open weights)
Contexte
Runs locally via faster-whisper, 6 GB GPU tested; Apache 2.0
Aucun changement de verdict pour l’instant
L’horloge tourne dès le premier jour : les changements apparaîtront ici à mesure que notre verdict évolue.
Sources
Journal de vérification
Aucune vérification pour le moment
Nous n’avons pas encore enregistré de vérification pour cette entrée. Dès qu’une vérification s’exécute, son historique apparaît ici.