單個 600M 模型取代 40 個語言檢查點
nvidia 的 nemotron 3.5 asr 在單個 600m 參數檢查點中支持 40 種語言，具有原生標點和通過 cache-aware fastconformer 實現的低延遲流式傳輸。
nvidia introduced nemotron 3.5 asr, a 600m-parameter speech model designed to handle 40 languages and dialects within a single unified checkpoint, removing the need for per-language deployments or separate punctuation models. the architecture utilizes a cache-aware fastconformer encoder to process audio frames exactly once, significantly reducing latency and compute costs while maintaining accuracy compared to traditional buffered streaming approaches. it features native output of punctuated and capitalized text, and offers optional language id conditioning for either specified or automatic language detection in mixed-language scenarios.