FlanEC maps five-candidate ASR lists to corrected transcripts and gets its best average word error rate (8.5%) from a 3B Flan-T5 model trained on all HyPoradise domains with full fine-tuning.
We define a specific instruction template and use it to create FlanEC us - ing HyPoradise dataset and leveraging the n-best lists gener- ated by an ASR model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
FlanEC: Exploring Flan-T5 for Post-ASR Error Correction
FlanEC maps five-candidate ASR lists to corrected transcripts and gets its best average word error rate (8.5%) from a 3B Flan-T5 model trained on all HyPoradise domains with full fine-tuning.