Improving RNN Transducer Based ASR with Auxiliary Tasks
Open paper
Benchmark
Model
Rank
Results
speech-recognition-on-librispeech-test-other
Transformer Transducer
#72
Word Error Rate (WER): 4.20
speech-recognition-on-librispeech-test-clean
Transformer Transducer
#75
Word Error Rate (WER): 2.0
Rank counts only results with a code link.