Semi-Supervised Speech Recognition via Local Prior Matching

Benchmark Model Rank Results
speech-recognition-on-librispeech-test-otherLocal Prior Matching (Large Model, ConvLM LM)#135Word Error Rate (WER): 15.28
speech-recognition-on-librispeech-test-otherLocal Prior Matching (Large Model)#137Word Error Rate (WER): 20.84
speech-recognition-on-librispeech-test-cleanLocal Prior Matching (Large Model)#136Word Error Rate (WER): 7.19