Whisper large-v3-turbo

model·speech recognition model·active

Pruned four-decoder-layer ASR checkpoint optimized for speed.

Recorded facts

Official site	https://huggingface.co/openai/whisper-large-v3-turbo ↗
Geography	unknown
parameter count	798M
huggingface repo	openai/whisper-large-v3-turbo
api	unknown
inputs	audio
license	MIT
outputs	text transcription
weights	public
modalities	audio; text transcription
dependencies	unknown
model family	Whisper
access method	downloadable weights; openai-whisper Python package; Hugging Face Transformers
exact version	large-v3-turbo
repository links	https://huggingface.co/openai/whisper-large-v3-turbo; https://github.com/openai/whisper
evaluation results	result: OpenAI reports performance similar to large-v2 overall, with larger degradation for some languages. · source: https://github.com/openai/whisper/discussions/2363 · benchmark: OpenAI multilingual comparison
evidence separation	developer claims: · measured results: · independent evaluations:
developer maintainer	OpenAI
material us relevance	Publicly accessible in or materially offered to the United States market as of snapshot.
documented capabilities	multilingual automatic speech recognition; lyric/vocal transcription as a downstream musical workflow
products exposing model	unknown
commercial use conditions	MIT terms apply to code and weights.
known geographic or policy restrictions	Turbo is not trained for speech translation
safety watermarking disclosure provenance	unknown