Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Streaming Automatic Speech Recognition on LibriSpeech (test-clean)
Loading...
3.1
WER
Transducer
3.06
3.33
3.6
3.87
May 12, 2026
WER
Updated 21d ago
Evaluation Results
Method
Method
Links
WER
Transducer
2026.05
3.1
Chunkwise Aligner
Alignment type=ground-...
2026.05
3.2
Chunkwise Aligner
Alignment type=ground-...
2026.05
3.4
Chunkwise Aligner
Alignment type=ground-...
2026.05
3.5
Chunkwise Aligner
Alignment type=streami...
2026.05
3.6
Chunkwise Aligner
Alignment type=ground-...
2026.05
3.9
CTC
2026.05
4.1
Feedback
Search any
task
Search any
task