List your company
ResearchFormerly WizWand

Speech Recognition on LibriSpeech 960hr (dev)

1.1WERwav2vec 2.0
1.061.331.61.87Aug 7, 2021
Updated 8mo ago

Evaluation results

MethodLinks
wav2vec 2.0Unlabeled Data (hrs)=60k, AM Size (B)=0.3, LM Size (B)=> 0.4, Training Strategy=Pre-training + Self-training, Decoding Strategy=With LM2021.081.1
wav2vec 2.0Unlabeled Data (hrs)=60k, AM Size (B)=0.3, LM Size (B)=> 0.4, Training Strategy=Pre-training + Self-training, Decoding Strategy=No LM2021.081.3
w2v-Conformer XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=No LM2021.081.3
w2v-Conformer XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=With LM2021.081.3
w2v-Conformer XXL+Unlabeled Data (hrs)=60k, AM Size (B)=1.1, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=No LM2021.081.3
w2v-Conformer XXL+Unlabeled Data (hrs)=60k, AM Size (B)=1.1, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=With LM2021.081.3
w2v-BERT XLUnlabeled Data (hrs)=60k, AM Size (B)=0.6, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=No LM2021.081.3
w2v-BERT XLUnlabeled Data (hrs)=60k, AM Size (B)=0.6, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=With LM2021.081.3
w2v-BERT XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=With LM2021.081.3
w2v-BERT XLUnlabeled Data (hrs)=60k, AM Size (B)=0.6, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.4
w2v-BERT XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.4
w2v-BERT XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training + Self-training, Decoding Strategy=No LM2021.081.4
HuBERT LargeUnlabeled Data (hrs)=60k, AM Size (B)=0.3, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.5
HuBERT X-LargeUnlabeled Data (hrs)=60k, AM Size (B)=1.0, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.5
w2v-Conformer XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.5
w2v-BERT XLUnlabeled Data (hrs)=60k, AM Size (B)=0.6, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=No LM2021.081.5
w2v-BERT XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=No LM2021.081.5
Conformer L with NSTUnlabeled Data (hrs)=60k, AM Size (B)=0.1, LM Size (B)=0.1, Training Strategy=Self-training Only, Decoding Strategy=No LM2021.081.6
Conformer L with NSTUnlabeled Data (hrs)=60k, AM Size (B)=0.1, LM Size (B)=0.1, Training Strategy=Self-training Only, Decoding Strategy=With LM2021.081.6
wav2vec 2.0Unlabeled Data (hrs)=60k, AM Size (B)=0.3, LM Size (B)=> 0.4+, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.6
w2v-Conformer XLUnlabeled Data (hrs)=60k, AM Size (B)=0.6, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=With LM2021.081.6
w2v-Conformer XXLUnlabeled Data (hrs)=60k, AM Size (B)=1.0, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=No LM2021.081.6
w2v-Conformer XLUnlabeled Data (hrs)=60k, AM Size (B)=0.6, LM Size (B)=0.1, Training Strategy=Pre-training Only, Decoding Strategy=No LM2021.081.7
Conformer LUnlabeled Data (hrs)=N/A, AM Size (B)=0.1, LM Size (B)=0.1, Training Strategy=Trained from Scratch, Decoding Strategy=No LM2021.081.9
wav2vec 2.0Unlabeled Data (hrs)=60k, AM Size (B)=0.3, LM Size (B)=> 0.4+, Training Strategy=Pre-training Only, Decoding Strategy=No LM2021.082.1