End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures

Open paper
Benchmark Model Rank Results
speech-recognition-on-librispeech-test-otherConv + Transformer AM (ConvLM with Transformer Rescoring)#70Word Error Rate (WER): 4.11
speech-recognition-on-librispeech-test-otherConv + Transformer AM (ConvLM with Transformer Rescoring) (LS only)#100Word Error Rate (WER): 5.18
speech-recognition-on-librispeech-test-cleanConv + Transformer AM + Pseudo-Labeling (ConvLM with Transformer Rescoring)#80Word Error Rate (WER): 2.03
speech-recognition-on-librispeech-test-cleanConv + Transformer AM (ConvLM with Transformer Rescoring) (LS only)#98Word Error Rate (WER): 2.31

Rank counts only results with a code link.