Home/Events/NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

Confirmed
Confidence
90%
Impact: 80%
Updated 6m ago

Consensus Brief

NVIDIA has released Nemotron 3.5 Transcribe, an open-weight model that provides multilingual transcription, speaker attribution, translation, and audio question answering. It supports 40 languages for transcription, translates 31 of them to or from English, and attributes speakers in 13 languages, achieving top rankings in various speech-to-text leaderboards.

Sourced from
Primary: Hugging Face

What Changed Since Last Update

6m ago

New official source added: Hugging Face published an update on Wed, 28 Oc ("NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt").

Claim Ledger

4 claims tracked across sources

Confirmed Fact

Nemotron 3.5 Transcribe ranks first among open-weight models on the Hugging Face Open ASR Leaderboard for English at 5.33% average WER.

Confirmed Fact

It transcribes 40 languages, translates 31 of them to or from English, and attributes speakers in 13.

Confirmed Fact

Fine-tuning cut word error rate (WER) on held-out speakers by 45.8% relative to the best prompt in a medical case study.

Confirmed Fact

Nemotron 3.5 Transcribe achieves 2.80% AA-WER with approximately 4B active parameters.

Role-Based Impact Analysis