Fine-tuning Whisper with overlapping 5-second context windows and embedded entity tags improves named entity recognition and formatting on Spoken Wikipedia, with the largest gains on numerical entities.
Title resolution pending
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
-
Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions
Fine-tuning Whisper with overlapping 5-second context windows and embedded entity tags improves named entity recognition and formatting on Spoken Wikipedia, with the largest gains on numerical entities.