Monsoon ASR dataset cuts Bengali Whisper word error rate to 7.65%
Original titleWER dropped from 85% to 7.65% on Bengali with one fine-tune.
AISummary
Voice Arena's Monsoon ASR dataset fine-tuned Whisper Medium on Bengali FLEURS, reducing LLM word error rate from 85.27% to 7.65%. The corpus spans 100,000 hours across 50 languages, and Voice Arena says more than 80 organisations have asked to license it since its launch a week ago.
Source: Elvis Saravia · x.comPublished · added here