Reson8 发布 1GB 端侧语音模型 Rumble-2-Flash
阿姆斯特丹初创公司 Reson8 发布 Rumble-2-Flash,仅 0.5B 参数、约 1GB 体积,可在手机端离线运行,覆盖 45 种语言并以 Apache 2.0 免费开源。该模型主打重口音、多人重叠、劣质电话线路与街头噪声等传统转写工具的失效场景,官方称其表现超过体积大 20 倍的模型。
报道正文
Rohan Paul (@rohanpaul_ai) · 2026-11-18 15
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.
↳ 引用 @raoulritterr (RR): 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