NVIDIA releases open-weight speech model Nemotron-3.5-Transcribe-30B-A4B
Original title: nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B (automatic-speech-recognition)
NVIDIA released Nemotron-3.5-Transcribe-30B-A4B, an open-weight offline speech model supporting transcription in 40 languages, speech translation, speaker diarization, timestamp prediction, and audio QA, with recordings up to 1 hour and a 65,536-token context. It uses a Mamba-2–Transformer hybrid MoE architecture with 34B total parameters and about 4.3B active (including the audio encoder), is available in BF16, FP8, and NVFP4, is based on Nemotron-3.5-Lightning-30B-A3B-BF16, and is licensed under OpenMDW-1.1 for commercial use.
Why it mattersThe README gives the model size, precision variants, and task coverage, letting readers judge whether it fits their transcription workflows.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.
Original article
Hugging Face 热门模型第 24 名：nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B，180 赞，近期下载 338 次。
标签：nemo, safetensors, nemo_speechlm, text2text-generation, nvidia, pytorch, nemotron-3.5, speech, asr, speech-translation, speaker-diarization, audio
README：
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
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
Model Overview
Description
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.
Model Summary
|
|
| Total Parameters |
34B (4.3B active), including the audio encoder |
| Architecture |
Mamba-2–Transformer hybrid Mixture of Experts language model with a Parallel Expert Encoder (Transformer ASR encoder and speaker encoder) |
| Precision |
BF16 (full-precision reference weights); FP8 and NVFP4 variants are available |
| Context Length |
65,536 tokens; recordings up to 1 hour |
| Inputs / Outputs |
Audio and text / text, with optional word timestamps |
| Languages |
40; see the language support matrix |
| Tasks |
Transcription in verbatim or written form, contextual transcription, |
The original belongs to Hugging Face 热门模型 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.
Studio