重點導讀
更多模型發布時,應該公開其基準測試工具。
AirCaps 剛推出 A5S Async v1,這是一款能追蹤每個詞是誰說的語音轉文字模型。他們也公開了程式碼、資料集製作方式、原始 API 回應,以及支撐測試結果的分數。
在他們測試的全部 5 個公開會議基準測試中,這款模型的錯誤率最低。
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
·13 天前
More model launches should publish their benchmark harness.
AirCaps just launched A5S Async v1, a speech-to-text model that tracks who said each word. They also published the code, dataset recipes, raw API responses, and scores behind their results.
It has the lowest error rate on all 5 public meeting benchmarks they tested.
推文來源 · X (Twitter)在 X 參與討論