模型69

Reson8 发布 1GB 语音转文字模型 Rumble-2-Flash

原标题:Amsterdam startup Reson8 has just released Rumble-2-Flash, a 1GB speech-to-text model that runs on a phone and beats models 20x its size.

Rohan Paul@rohanpaul_ai发布时间 (北京时间)

阿姆斯特丹创业公司 Reson8 发布语音转文字模型 Rumble-2-Flash,仅 0.5B 参数、体积 1GB,可在手机上本地运行。该模型覆盖 45 种语言,以 Apache 2.0 协议免费开放权重,针对重口音、多人重叠说话、音质差的电话线路和街头噪声等场景做了优化。作者称其在手机上离线即可转写通话和语音笔记,并认为小体量开源模型在语音识别上正快速缩小与前沿系统的差距。

中文译文尚未完成,先为你展示原文。

Amsterdam startup Reson8 has just released Rumble-2-Flash, a 1GB speech-to-text model that runs on a phone and beats models 20x its size.

Just 0.5B parameters, covers 45 languages and is free under Apache 2.0, built for the audio that breaks most transcription tools: thick accents, overlapping voices, bad phone lines and street noise.

Running on the phone itself, it would transcribe calls and voice notes with no internet connection.

Speech recognition is one of the places where very small open models are closing the gap with frontier systems fastest.

Rumble-2-flash is open weights you can get it in all your favorite places. It’s better than models 20x it’s size small enough to run on your phone HF link below
查看原帖
语音与音频开源生态模型发布#模型发布#语音#开源生态#Hugging Face

同一件事的其他报道2 篇