Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Open paper
Benchmark Model Rank Results
speech-recognition-on-wsj-eval92Deep Speech 2#6Word Error Rate (WER): 3.60
speech-recognition-on-librispeech-test-cleanDeep Speech 2#132Word Error Rate (WER): 5.33
speech-recognition-on-librispeech-test-otherDeep Speech 2#134Word Error Rate (WER): 13.25

Rank counts only results with a code link.