Proposes Weighted-Attention and Self-Conditioning to reduce decoder inconsistencies and WER in Whisper for Dravidian and low-resource languages.
Outlier reduction with gated attention for improved post-training quanti- zation in large sequence-to-sequence speech foundation models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages
Proposes Weighted-Attention and Self-Conditioning to reduce decoder inconsistencies and WER in Whisper for Dravidian and low-resource languages.