Open-weight speech recognition. 2.7% WER on clean audio. Supports 99 languages.
Each score is anchored to human baseline (100). Source URLs link to the original benchmark, leaderboard, or release note.
| Sub-capability | Quality | Source | Score vs. baseline | Score |
|---|---|---|---|---|
| Speaker Identification | independent | paperswithcode.com/sota/speaker-verification-on-voxceleb1 | 94% | |
| Speech Recognition | independent | openai.com/research/whisper | 103% |