wav2vec_wav2letter

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

Speech RecognitiononLibriSpeech train-clean-100 test-other
Word Error Rate (WER)· uses extra data· 2020-10-22
3.6
SOTA
Self-training and Pre-training are Complementary for Speech Recognition arXiv:2010.11430
Speech RecognitiononLibriSpeech train-clean-100 test-clean
Word Error Rate (WER)· uses extra data· 2020-10-22
2.8
SOTA
Self-training and Pre-training are Complementary for Speech Recognition arXiv:2010.11430
Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· 2020-10-22
2.7
best: 0.985 (United Med ASR)
Self-training and Pre-training are Complementary for Speech Recognition arXiv:2010.11430