Speech Recognition On Common Voice German
Métriques
Test WER
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Test WER |
|---|---|
| nemo-a-toolkit-for-building-ai-applications | 6.68% |
| tevr-improving-speech-recognition-by-token | 3.64% |
| robust-speech-recognition-via-large-scale-1 | 6.4% |
| tevr-improving-speech-recognition-by-token | 3.70% |
| tevr-improving-speech-recognition-by-token | 4.38% |
| automatic-speech-recognition-in-german-a | 6.28% |
| scribosermo-fast-speech-to-text-models-for | 6.6% |
| voxpopuli-a-large-scale-multilingual-speech | 7.8% |
| nemo-a-toolkit-for-building-ai-applications | 6.03% |
| tevr-improving-speech-recognition-by-token | 12.06% |
| scribosermo-fast-speech-to-text-models-for | 4.05% |
| scribosermo-fast-speech-to-text-models-for | 7.7% |
| tevr-improving-speech-recognition-by-token | 10.10% |
| scribosermo-fast-speech-to-text-models-for | 7.33% |