Seven Akan ASR models were evaluated across four domains, showing strong in-domain performance but weak generalization, with Whisper and Wav2Vec2 producing distinct error types.
Developing an open-source corpus of yoruba speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Akan ASR Models Across Domain-Specific Datasets: A Comparative Evaluation of Performance, Scalability, and Adaptability
Seven Akan ASR models were evaluated across four domains, showing strong in-domain performance but weak generalization, with Whisper and Wav2Vec2 producing distinct error types.