Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Speaker-attributed Automatic Speech Recognition on AISHELL-4
Loading...
21.36
WER
GLSC-SDR
20.956
23.683
26.41
29.137
Mar 26, 2026
WER
cpWER
Δcp
SCA
Updated 22d ago
Evaluation Results
Method
Method
Links
WER
cpWER
Δcp
SCA
GLSC-SDR
2026.03
21.36
23.49
2.13
90.96
ViebVoice-ASR
2026.03
21.4
24.99
3.59
-
Gemini-2.5-pro*
source=converted from...
2026.03
22.42
31.59
9.17
-
Gemini-3-pro*
source=converted from...
2026.03
22.75
27.43
4.68
-
Qwen2.5-omni-sft
mode=fine-tuned
2026.03
23.83
26.34
2.51
89.93
Qwen2.5-omni
2026.03
31.46
46.28
14.82
76.68
Feedback
Search any
task
Search any
task