Official announcement · Hugging Face · Wednesday 28 October

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

NVIDIA's Speech research team has released Nemotron 3.5 Transcribe and Granary v2, described as open, state-of-the-art, production-ready enterprise speech models for ASR, TTS, Speaker Diarization and S2S. The Nemotron 3.5 Transcribe model is 34B parameters, alongside a 99.2M-parameter Voice Activity Detection model, offering multilingual transcription that can be prompted and adapted.

Read at huggingface.co The opening of the original, or for stories before 30 October 2026 an AI model's summary of it. Check the original before you rely on a detail.

More from Hugging Face

All stories

Hugging Face

OfficialHugging Face

Granite Switch 4.1.1 — Update models like you update software

Granite Switch 4.1.1 offers modular Granite models with built-in adapters that switch on as needed from a single checkpoint, delivering chat, decisions, and speech from one endpoint. The update also introduces Granite Speech 5.0 for more accurate and faster transcription, translation, and attribution.

1 day ago

OfficialHugging Face

Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms

Hugging Face introduced AnySpeechRecognizer and AnyDecisionModel, open models for speech recognition and decision-making on Apple platforms. The announcement sits within the broader AnyLanguageModel initiative, which provides a single API for local and remote LLMs on Apple platforms and marks one year of local models on those platforms.

2 days ago

OfficialHugging Face

Announcing Project ProtoStar: Making Publicly Funded Science AI-Ready

An initiative bringing together universities, research organizations, industry, and the open science community to make publicly funded research easier to discover, reuse, and build upon.

2 days ago

Hugging Face

OfficialHugging Face

Build specialized multimodal models with LFM3

This Hugging Face page presents LFM3, a family of specialized multimodal models from Liquid AI. It lists several LFM3 model variants—Text Generation (8B and 2B), Any-to-Any (2B), and Image-Text-to-Text (2B and 3B)—and links to a collection of base and post-trained LFM3 models hosted at liquid.ai/blog/lfm3. Related posts from the same author cover running private agents on-device with LFM2.5-24B-A2B and multimodal open decision models for the edge.

3 days ago