Chinese contentVoice Arena 推出基于真实对话的语音识别基准测试
Voice Arena 搞了个语音识别基准，用真实对话测 ASR，不是念稿子，首套覆盖 5 种语言，做语音的可以去刷榜了。
#Monsoon
5 stories · 0 in 7 days · 1 in 30 days
Stories, products and papers tagged "Monsoon", newest first.
Nov 6
Oct 9
Chinese contentVoice Arena 发布 Monsoon 语音数据集：50 种语言、10 万小时
Monsoon 是个 10 万小时的多语言语音数据集，微调 Whisper 后孟加拉语词错率从 85% 降到 7.65%，做语音方向的可以试试 API 测测效果。
Chinese contentVoice Arena 语音数据集 Monsoon 发布，孟加拉语 WER 微调后降至 7.65%
微调 Whisper Medium 就把孟加拉语 WER 从 85% 打到 7.65%，80 多家机构一周内排队要授权，低资源语音方向的值得关注。
Whisper Medium Cuts Bengali WER to 7.65% via Monsoon Fine-tuning
The numbers suggest teams working on under-served languages should invest in corpus collection before paying for larger models. The 769M-parameter size also makes on-device or edge deployment realistic for markets like Bangladesh and India where Bengali ASR options remain thin. Developers can reproduce the setup with open Whisper checkpoints and the Monsoon dataset.
Sep 28
Monsoon speech dataset cuts Telugu WER from 92.7% to 16.1%
The takeaway is that low-resource ASR quality can be bought with better data curation rather than bigger models, since a mid-size Whisper checkpoint beat Gemini 3.1 Pro on Telugu purely through fine-tuning. Teams building speech products for Indic and other under-served language markets can use this dataset-first approach instead of waiting for larger architectures. Keeping noisy audio in training, with DNSMOS-based stratification, is the transferable technique.