Open-weight & owned stack · Open lab releases
Nvidia Releases Open Nemotron Transcribe And Granary
Nvidia released the open-weight Nemotron 3.5 Transcribe model with Granary v2, an open speech dataset covering 463,062 hours, for multilingual transcription, translation, diarization, and audio questi
Read the original at huggingface.coOpens the publisher's site in a new tabAlso covering this
Nvidia debuts Nemotron 3.5 Transcribe, an open-weight model for multilingual audio transcription and translation, and Granary v2, its open-source speech dataset (Kyt Dotson/SiliconANGLE)siliconangle.com, Oct 28Voice AI in vogue: Nvidia releases new open transcription modeltechcrunch.com, Oct 28NVIDIA Expands Open-Weight Model Family with Nemotron 3.5 Audio Transcription and Translation Release — OODAloopoodaloop.com, Oct 28Voice AI in vogue: Nvidia releases new open transcription modelbiztoc.com, Oct 28Nvidia releases Nemotron 3.5 ASR, a free open-weight model for 40-language audio transcriptioncryptobriefing.com, Oct 28Nvidia launches a promptable transcription model - The New Stackthenewstack.io, Oct 28Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognitionthe-decoder.com, Oct 28NVIDIA Nemotron 3.5 Transcribe. The same model. The same audio. A… | by Cobus Greyling | Oct, 2026 | Mediumcobusgreyling.medium.com, Oct 28