nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
automatic-speech-recognition model by nvidia
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Nemotron 3.5 Transcribe is an open-weight, offline speech and audio model for transcription in 40 languages, with support for recordings up to one hour and a 65,536-token context. Its hybrid mixture-of-experts architecture activates approximately 4.3B parameters, including the audio encoder, and it is released in BF16, FP8, and NVFP4 precision. Get started ↓ · Explore the tasks ↓ · See the evidence ↓ · NeMo Speech ↗ Table of contents NVIDIA Nemotron-3.5-Transcribe is an offline speech and audio model that processes recordings, together with text instructions and optional context, into text responses. NVIDIA developed this Speech-Augmented Language Model (SALM) for multilingual transcription, speech translation, contextual transcription, speaker-attributed transcription, rich transcription, timestamp prediction, language identification, and audio question answering. The training mixture also includes a small amount of text instruction following and PII tagging/redaction tasks. This model is ready for commercial or non-commercial use. Results captured on October 12, 2026. Error…
Read the full model card ↗ · Preview checked 2026-10-29T09:56:46.390Z
Inside the original model card — Document outline
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
- Model Overview
- Description
- Model Summary
- Results at a Glance
- Efficiency
- Quick Start
- Prompt Guide
- License / Terms of Use
- Deployment Geography
- Use Case
- Release Date
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is a automatic-speech-recognition model repository published by nvidia on Hugging Face. The source reports the nemo library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- automatic-speech-recognition
- Library
- nemo
- Recent downloads (30 days)
- 24,357
- Cumulative likes
- 554
- Hugging Face trending score
- 512
- Reported safetensors parameters
- 33,697,781,029
- Architecture
- Nemotron3_5TranscribeForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-07T22:50:21.000Z
- Last modified
- 2026-10-29T23:04:39.000Z
Compatibility and lineage
Reported languages: cs, nl, en, fr, de, hi, it, ko, pl, pt, ru, sk, es, bg, hr, da, et, fi, hu, ja, lv, lt, ro, sl, sv, th, tr, uk, ar, bn, zh, el, he, id, mt, mr, tl, ta, te, vi
Reported base models: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
jonatasgrosman/wav2vec2-large-xlsr-53-japanese