On fine-tuned Bangla ASR, Wav2Vec-BERT outperformed Whisper Small and Large-v2 in WER and CER while using less training time and smaller hardware.
A comparison of sequence-to-sequence models for speech recognition
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
-
Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
On fine-tuned Bangla ASR, Wav2Vec-BERT outperformed Whisper Small and Large-v2 in WER and CER while using less training time and smaller hardware.