Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Streaming Automatic Speech Recognition on STOP2
Loading...
9.66
WER
Streaming CTC-WS
9.5628
10.2189
10.875
11.5311
May 18, 2026
WER
F-score
Precision
Recall
Updated 15d ago
Evaluation Results
Method
Method
Links
WER
F-score
Precision
Recall
Streaming CTC-WS
Decoder=RNN-T, Chunk S...
2026.05
9.66
95.6
97.47
93.79
GPU-PB
Decoder=RNN-T, Chunk S...
2026.05
10.18
93.62
96.83
90.62
Non-biasing Baseline
Decoder=RNN-T, Chunk S...
2026.05
10.43
92.16
98.6
86.51
Streaming CTC-WS
Decoder=CTC, Chunk Siz...
2026.05
10.48
95.06
97.35
92.88
GPU-PB
Decoder=CTC, Chunk Siz...
2026.05
11.86
90.53
98.05
84.09
Non-biasing Baseline
Decoder=CTC, Chunk Siz...
2026.05
12.09
88.26
98.76
79.79
Feedback
Search any
task
Search any
task