SN-WER normalizes scripts via transliteration before WER computation, reducing apparent model gaps by up to 12% on FLEURS data for five Indic languages while remaining sensitive to real lexical errors.
Advocating Character Error Rate for Multilingual ASR Evaluation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Fine-tuned edge ASR models reduce WER by 26.9 points over zero-shot baselines on 19 African languages while being substantially smaller and release supporting artifacts.
citing papers explorer
-
SN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation
SN-WER normalizes scripts via transliteration before WER computation, reducing apparent model gaps by up to 12% on FLEURS data for five Indic languages while remaining sensitive to real lexical errors.
-
WAXAL-NET: Finetuned Edge ASR Across 19 African Languages
Fine-tuned edge ASR models reduce WER by 26.9 points over zero-shot baselines on 19 African languages while being substantially smaller and release supporting artifacts.