Librispeech Transducer Model with Internal Language Model Prior Correction
Open paper
Benchmark
Model
Rank
Results
speech-recognition-on-librispeech-test-clean
LSTM Transducer
#95
Word Error Rate (WER): 2.23
speech-recognition-on-librispeech-test-other
LSTM Transducer
#104
Word Error Rate (WER): 5.6
Rank counts only results with a code link.