EG-seq2seq
Reported on 3 benchmarks across 3 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Speech1 result
- Word Error Rate (WER)· uses extra data· 2020-05-126.8best: 0.74 (MMS-LLaMA)
Computer Vision1 result
- Word Error Rate (WER)· 2020-05-1257.8best: 12.8 (LP + Conformer)
Natural Language Processing1 result
- Word Error Rate (WER)· 2020-05-1257.8best: 12.8 (LP + Conformer)