HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

openai/whisper-large-v3-turbo

family misc · 73 variants · unknown

provider
openai
released
—
huggingface
https://huggingface.co/openai/whisper-large-v3-turbo
best scores
WER: 68.79CER: 27.8RTF: 6.5WER Common Voice: 64.0WER FLEURS: 50.84WER LibriSpeech: 17.9WER SPGISpeech: 1.92WER TED-LIUM: 3.37WER VoxPopuli: 7.37WER GigaSpeech: 9.56WER Earnings-22: 11.57WER AMI: 21.4WER MLS: 6.89

Best scores per benchmark

benchmarkcategorybest score

Variants (73)

variantkindquantbitsvRAMdlorgyear
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.