SAMBA ASR

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

Speech RecognitiononGigaSpeech DEV
Word Error Rate (WER)· 2025-01-06
9.12
SOTA
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models arXiv:2501.02832
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2025-01-06
2.48
SOTA
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models arXiv:2501.02832
Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· uses extra data· 2025-01-06
1.17
best: 0.985 (United Med ASR)
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models arXiv:2501.02832