Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Unsupervised Automatic Speech Recognition on LibriSpeech 100 hours (dev-other)
Loading...
8.5
PER
REBORN
7.924
11.812
15.7
19.588
Feb 6, 2024
PER
WER
Updated 4d ago
Evaluation Results
Method
Method
Links
PER
WER
REBORN
Self-training=HMM ST
2024.02
8.5
13.5
Train from oracle
Boundary=Oracle
2024.02
9.7
16.3
REBORN
2024.02
11.9
17.6
wav2vec-U 2.0
Reproduction=true, Sel...
2024.02
13.1
19
wav2vec-U 2.0
Reproduction=true
2024.02
16.3
21.7
EURO
Backbone=HuBERT
2024.02
20.7
29.3
wav2vec-U
Reproduction=true
2024.02
22.9
25.6
Feedback
Search any
task
Search any
task