Whisper large-v3
OpenAI · Veröffentlicht 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.
Ist es das Richtige für dich?
Gut für
- 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
Nicht geeignet für
- 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
Preise
Eingabe
Free (self-hosted open weights)
Ausgabe
Free (self-hosted open weights)
Kontext
Runs locally via faster-whisper, 6 GB GPU tested; Apache 2.0
Noch keine Urteilsänderungen
Die Uhr läuft ab dem ersten Tag. Änderungen erscheinen hier, sobald sich unser Urteil weiterentwickelt.
Quellen
Prüfprotokoll
Noch keine Prüfungen
Wir haben für diesen Eintrag noch keine Prüfung erfasst. Sobald eine Prüfung läuft, erscheint ihr Verlauf hier.