# NVIDIA Nemotron 3.5 ASR: 600M-Parameter Multilingual Speech-to-Text

NVIDIA Nemotron 3.5 ASR is a 600M-parameter streaming speech recognition model covering 40 language-locales from a single checkpoint. Open weights, OpenMDW-1.1 license.

## What Is Nemotron 3.5 ASR?

**NVIDIA Nemotron 3.5 ASR** is a **600M-parameter streaming Automatic Speech Recognition (ASR) model** released on **June 4, 2026**. It's part of NVIDIA's Nemotron Speech ecosystem within the NeMo framework.

The key achievement: **a single checkpoint covers 40 language-locales** — no per-language models, no model-swapping. The model transcribes in real time with native punctuation and capitalization built in, producing production-ready text without a separate punctuation-restoration step.

Open weights are available on [Hugging Face](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b) under the **OpenMDW-1.1 license**.

## Architecture: Cache-Aware FastConformer-RNNT

Nemotron 3.5 ASR uses a **Cache-Aware FastConformer-RNNT** architecture — an evolution of NVIDIA's original English streaming model `nvidia/nemotron-speech-streaming-en-0.6b`.

Key architectural innovations:

-
- **FastConformer backbone** — Efficient attention mechanism optimized for streaming audio

-
- **Cache-aware design** — Maintains a sliding window cache of previous audio frames, eliminating the latency drift found in traditional sliding-window models

-
- **RNNT loss** — RNN Transducer loss for accurate sequence-to-sequence speech recognition

-
- **Prompt-based language-ID conditioning** — A single model handles all 40 language-locales through conditional prompting

This architecture directly addresses a fundamental limitation of Whisper and similar models: **sliding-window ASR systems suffer from latency drift** as the window shifts through long audio streams. Nemotron 3.5's cache-aware approach keeps latency stable throughout the entire audio duration.

## Target Workloads

Nemotron 3.5 ASR targets two primary workloads:

| **Workload** | **Use Case** | **Key Feature**|
--- | --- | ---
| **Streaming** | Live audio transcription, real-time captioning, voice assistants | Low-latency, stable through entire stream|
| **Batch** | Meeting recordings, podcast transcription, video subtitles | High-throughput, production-ready output|

## Language Support: 40 Language-Locales

A single 600M-parameter model covers **40 language-locales**, including:

- English (US, UK, AU, IN), Spanish (ES, MX), French (FR, CA), German

- Italian, Portuguese (BR, PT), Dutch, Russian, Japanese, Korean

- Chinese (Mandarin), Hindi, Arabic, Turkish, Polish, Swedish

- Danish, Finnish, Norwegian, Thai, Vietnamese, Indonesian, and more

This multilingual capability in a single checkpoint is a significant advantage over models like Whisper, which require separate models for different language modes.

## Benchmark Performance

While NVIDIA hasn't published a comprehensive benchmark table, the model is positioned as competitive with Whisper on standard English benchmarks and superior on streaming-specific metrics:

-
- **Streaming latency** — Lower and more stable than Whisper's sliding-window approach

-
- **Clinical ASR** — NVIDIA's own clinical workflow evaluation shows competitive results on medical terminology recognition

-
- **Multilingual WER** — Competitive word error rates across supported languages

NVIDIA has published a **clinical ASR evaluation workflow** (June 9, 2026) using Nemotron Speech for evaluating pronunciation accuracy on rare medical terminology — drug names, procedure names, and specialty-specific diagnoses.

## Deployment & Ecosystem

Nemotron 3.5 ASR integrates into NVIDIA's broader ecosystem:

-
- **NVIDIA NeMo Data Designer** — For data preparation and synthetic data generation

-
- **Magpie TTS Multilingual** — For creating pronunciation-aware synthetic training data

-
- **NVIDIA Agent Skills** — For automated clinical ASR evaluation workflows

-
- **DGX Spark / arm64** — Edge deployment support for on-device transcription

# NVIDIA Nemotron 3.5 ASR (Hugging Face)
# Model: nvidia/nemotron-3.5-asr-streaming-0.6b
# License: OpenMDW-1.1

from transformers import AutoModel

model = AutoModel.from_pretrained("nvidia/nemotron-3.5-asr-streaming-0.6b")
# Transcribe with language conditioning
result = model.transcribe(
audio="recording.wav",
language="en-US", # or "es-MX", "ja-JP", etc.
streaming=True
)

## Clinical ASR Applications

NVIDIA has demonstrated Nemotron 3.5 ASR's capability in the **clinical domain**, where accuracy on rare medical terminology is critical. Drug names like Acetaminophen, Amlodipine, Cefazolin, and Biktarvy are not part of everyday vocabulary — off-the-shelf speech systems can sound fluent and still miss the words that matter most.

The clinical workflow uses **synthetic data generation (SDG)** to create pronunciation-aware evaluation datasets without real patient data, enabling rapid benchmark creation without HIPAA compliance overhead.

### Key Takeaways

• NVIDIA Nemotron 3.5 ASR: 600M-parameter, 40 language-locales in one checkpoint

• Cache-Aware FastConformer-RNNT architecture — beats sliding-window latency drift

• Native punctuation and capitalization — production-ready output

• Open weights on Hugging Face under OpenMDW-1.1 license

• Targets streaming (live) and batch (recording) workloads

## Related Articles

[**Qwen-AgentWorld 35B-A3B**](/qwen-agentworld-35b-a3b-open-source.html) — Language World Models for General Agents
[**Best AI Models for Hermes Agent**](/top-ai-models-for-hermes-agent-local-and-cloud.html) — Local and cloud deployment options