Deep Speech: Scaling up end-to-end speech recognition

Open paper Other version
Benchmark Model Rank Results
human-pose-forecasting-on-human36m-absoluteDeepSpeech#16Average MPJPE (mm) @ 1000 ms: 198
speech-recognition-on-swb-hub-500-werCNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWB#1Percentage error: 16
speech-recognition-on-switchboard-hub500Deep Speech + FSH#1Percentage error: 12.6
speech-recognition-on-switchboard-hub500CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWB#2Percentage error: 12.6
speech-recognition-on-switchboard-hub500Deep Speech#5Percentage error: 20

Rank counts only results with a code link.