重點導讀
語音轉文字遇到口音、多人同時說話或背景噪音時,常常會出錯。
- Reson8 推出免費的語音轉文字模型 Rumble-2-Flash,訓練時使用容易讓這類系統出錯的音訊,支援40多種語言。
- 模型採用 Apache 2.0 授權,使用者可以在自己的裝置上執行,讓音訊留在本機。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
elvis@omarsar0
·4 天前
Speech-to-text still breaks on real-world audio.
Rumble-2-Flash from Reson8 is a free, open-weights speech-to-text model trained on audio that usually trips up these systems. Think heavy accents, people talking over each other, phone calls, and background noise.
It covers 40+ languages. The weights are Apache 2.0, so you can run it on your own machine and keep your audio local.
推文來源 · X (Twitter)在 X 參與討論