Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Speaker-attributed Automatic Speech Recognition on AMI SDM
Loading...
17.49
WER
GLSC-SDR
16.8996
20.8848
24.87
28.8552
Mar 26, 2026
WER
cpWER
Δcp
SCA
Updated 22d ago
Evaluation Results
Method
Method
Links
WER
cpWER
Δcp
SCA
GLSC-SDR
2026.03
17.49
23.32
5.83
76.67
Qwen2.5-omni-sft
mode=fine-tuned
2026.03
20.23
27.16
6.93
74.33
Gemini-3-pro*
source=converted from...
2026.03
22.09
26.91
4.82
-
Gemini-2.5-pro*
source=converted from...
2026.03
22.35
34.78
12.43
-
ViebVoice-ASR
2026.03
24.65
28.82
4.17
-
TagSpeech
2026.03
31.62
42.55
10.93
70.01
Qwen2.5-omni
2026.03
32.25
49.86
17.61
60.06
Feedback
Search any
task
Search any
task