The paper releases Sagalee, a 100-hour, 283-speaker Oromo ASR dataset, and reports baseline WERs of 15.32% (Conformer AED), 18.74% (Conformer CTC), and 10.82% (Whisper Large-v3 fine-tuned).
Some aspects of oromo history that have been misunderstood,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language
The paper releases Sagalee, a 100-hour, 283-speaker Oromo ASR dataset, and reports baseline WERs of 15.32% (Conformer AED), 18.74% (Conformer CTC), and 10.82% (Whisper Large-v3 fine-tuned).