Automatic Speech Recognition on Supreme-court-speech
15.5WERparakeet-rnnt-1.1b
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| parakeet-rnnt-1.1bparameters=1.1B, architecture=RNNT2025.02 | 15.5 | 15.3 | 17.4 | 18.8 | — | |
| parakeet-tdt-1.1bparameters=1.1B, architecture=TDT2025.02 | 15.7 | 15.5 | 15.7 | 19.1 | — | |
| canary-1bparameters=1B2025.02 | 16 | 15.7 | 18.9 | 21.3 | — | |
| whisper-large-v3-turboModel Size=Large, Version=v3-turbo2025.02 | 18.5 | — | — | — | 13.8 | |
| whisper-mediumModel Size=Medium2025.02 | 18.7 | — | — | — | 14.4 | |
| whisper-large-v3Model Size=Large, Version=v32025.02 | 18.8 | — | — | — | 15.4 | |
| distil-large-v2Model Size=Large, Type=Distilled, Version=v22025.02 | 18.9 | — | — | — | 14.3 | |
| wav2vec2-large-xlsr-53-englishModel Size=Large, Architecture=wav2vec2-xlsr2025.02 | 32.6 | — | — | — | 14.8 | |
| Qwen2-Audio-7BArchitecture=Qwen2, Parameters=7B2025.02 | 35.3 | — | — | — | 37.1 |