Automatic Speech Recognition in German: A Detailed Error Analysis

Open paper
Benchmark Model Rank Results
speech-recognition-on-common-voice-germanConformer Transducer (no LM)–Test WER: 6.28%
speech-recognition-on-tudaConformer-Transducer (no LM)–Test WER: 5.82%

Rank counts only results with a code link.