Speech to text · OpenAI
Whisper large-v3
The multilingual reference ASR model.
Datasheet
Maker | OpenAI |
|---|---|
Parameters | 1.54 BVerifiedsafetensors.total from the HF API Source |
Licence | Apache-2.0Verified |
Access | Public download |
Task (HF pipeline) | automatic-speech-recognition |
First published on HF | 2023-11-07 |
Last updated on HF | 2024-08-12 |
Weights in memory | 3.1 GB at 16-bit · 0.9 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build. |
Benchmark
7.84%
Open ASR Leaderboard, average WER (English short-form) · #6 of 7 scored in this category
avg 7.8414, RTFx 470.73. Source
Used in
The description summarises the model card at https://huggingface.co/openai/whisper-large-v3. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.