Speech Recognition On Tedlium
Metriken
Word Error Rate (WER)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Word Error Rate (WER) |
|---|---|
| speechstew-simply-mix-all-available-speech | 5.3 |
| fast-conformer-with-linearly-scalable | 3.92 |
| high-precision-medical-speech-recognition | 0.29 |
| hyporadise-an-open-baseline-for-generative-1 | 4.6 |