Model card
Whisper Large-v2.
OpenAIopen-source1.5B paramsTransformer encoder-decoder
OpenAI Whisper (arXiv 2212.04356).
§ 01 · Benchmarks
Every benchmark Whisper Large-v2 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Common Voice | Speech · Speech Recognition | wer | 11.2% | #1 | 2022-12-06 | source ↗ |
| 02 | LibriSpeech | Speech · Speech Recognition | wer-test-clean | 2.7% | #1 | 2022-12-06 | source ↗ |
| 03 | LibriSpeech | Speech · Speech Recognition | wer-test-other | 5.2% | #1 | 2022-12-06 | source ↗ |
| 04 | MuST-C En-De tst-COMMON | Speech · Speech Translation | bleu | 29.0% | #2 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for Whisper Large-v2.
- 2022-12-06· Speech· 3 results
Robust Speech Recognition via Large-Scale Weak Supervision (Whisper)
§ 04 · Related models
Other OpenAI models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
editorial
1
result
3 of 4 rows marked verified.