Voice Arena launches Monsoon ASR corpus; one fine-tune cuts Bengali WER from 85.27% to 7.65%
Overview
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.
Written by AI from one article, by Elvis Saravia
Check the sources:
Article timeline
Follow the coverage from different perspectives. Times are ET.
- Elvis SaraviaMonsoon ASR dataset cuts Bengali Whisper word error rate to 7.65%
AIVoice 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.
Heat trend
Not enough continuous observations to show a trend yet.