There are recipes to reproduce results from the following papers:
mls
MLS: A Large-Scale Multilingual Dataset for Speech Research, 2020local_prior_match
Semi-Supervised Speech Recognition via Local Prior Matching, 2020streaming_convnets
Scaling Up Online Speech Recognition Using ConvNets, 2020sota/2019
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures, 2020self_training
Self-Training for End-to-End Speech Recognition, 2020seq2seq_tds
Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions, 2019learnable_frontend
Learning Filterbanks from Raw Speech for Phone Recognition), 2018lexicon_free
Who Needs Words? Lexicon-Free Speech Recognition, 2019conv_glu
Wav2Letter: an End-to-End ConvNet-based Speech Recognition System, 2016