Nvidia releases open Nemotron 3.5 Transcribe model combining transcription, translation and speaker recognition

Nvidia has released Nemotron 3.5 Transcribe, an open speech recognition model that processes text instructions to handle transcription, translation, and speaker identification in a single system. The model supports 40 languages for transcription and 31 for translation, and can identify speakers across 13 languages. It handles recordings up to an hour long with up to eight speakers. According to Nvidia, the model ranks first among open-weight models on Hugging Face's English Open ASR Leaderboard with a 5.33 percent average word error rate, and scores 2.81 percent on Artificial Analysis benchmarks, approaching top closed models while using significantly less compute. It also leads in speaker recognition, outperforming 14 tested systems on VoiceArena's benchmark.