All benchmarksTest WER (lower is better)
Common Voice 11.0 (hi), Test WER
As the model cards publish them, each model’s best result. Facthory has not run them; results are self-reported unless the hub verified them.
| # | Model | Result | Source |
|---|---|---|---|
| 1 | whisper-medium openai · test | 53.87 | Model card |
| 2 | whisper-large openai · test | 54.8 | Model card |
| 3 | whisper-small openai · test | 87.3 | Model card |
| 4 | whisper-base openai · test | 131 | Model card |
| 5 | whisper-tiny openai · test | 141 | Model card |
