600M 모델 하나가 교체 작업 없이 40개 언어 체크포인트를 대체
NVIDIA의 Nemotron 3.5 ASR은 단일 600M 파라미터 체크포인트로 40개 언어를 지원하며, cache-aware FastConformer를 통해 네이티브 문장부호 처리와 저지연 스트리밍을 제공한다.
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.