Briefs

BriefsNewsAvailable now1 min read

Nvidia releases Nemotron 3.5 Transcribe and Granary v2

Nvidia launches Nemotron 3.5 Transcribe, an open-weight multilingual speech model, alongside the Granary v2 data curation pipeline and fine-tuning tools.

Nvidia releases Nemotron 3.5 Transcribe and Granary v2 — image from Hugging Face
Image: Hugging Face

Summary

Nvidia has released Nemotron 3.5 Transcribe, an open-weight multilingual speech model capable of transcription, speaker attribution, translation, and audio question answering. The model handles up to 40 languages and runs on a single Nvidia GPU. Alongside the model, Nvidia released Granary v2, a multilingual data curation pipeline, and fine-tuning recipes for domain adaptation.

What changed

  • Released the open-weight Nemotron 3.5 Transcribe model for multilingual transcription, translation, speaker attribution, and audio Q&A.
  • Released the Granary v2 data curation pipeline and public manifests on Hugging Face and ModelScope.
  • Released NeMo Speech fine-tuning recipes to adapt recognition to domain vocabulary and accents.

Availability

Available now

“NVIDIA Nemotron 3.5 Transcribe is an open-weight, promptable model that turns recorded speech into useful text, now available on Hugging Face and ModelScope .”

Founder takeaway

Small teams building audio applications can evaluate Nemotron 3.5 Transcribe on Hugging Face or ModelScope for multilingual transcription, speaker diarization, and domain adaptation using the provided fine-tuning tools.

Source

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

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. AWS logo on a FounderHeist card

    NewsAvailable now

    Amazon Quick adds smart approvals for agentic AI actions

    Amazon Quick introduces smart approvals to automate routine agentic tasks while keeping human oversight for high-impact actions.

    AWS1 min read

  2. ElevenLabs introduces Cue forced alignment AI model — image from ElevenLabs

    NewsAvailable now

    ElevenLabs introduces Cue forced alignment AI model

    ElevenLabs releases Cue, an AI forced alignment model that places every character in an audio file on a precise timeline and powers its Scribe model family.

    ElevenLabs1 min read

  3. GitHub makes Copilot Memory generally available on paid Copilot plans — image from GitHub

    NewsAvailable now

    GitHub makes Copilot Memory generally available on paid Copilot plans

    GitHub introduces new AI intelligence capabilities including Copilot Memory, dreaming, and multi-repository code search.

    GitHub1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.