How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up Back to Articles a]:hidden"> How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent Community Article Published June 4, 2026 Upvote 57 +51 Maryam Motamedi maryameee Follow nvidia Francesco fciannella Follow nvidia Myungjong Kim Myungjong Follow nvidia Enas Albasiri enas-albasiri Follow nvidia Jinhan Wang Jinhanw Follow nvidia Yitagessu Gebremedhin Yitagessu Follow nvidia The problem with multilingual speech recognition today What it does How it works (the 2-minute version) att_context_size</code>"> A knob worth knowing: att_context_size Try it in minutes Why fine-tune? A Preview of the Power of Fine-Tuning The recipe at a glance Step 1 — Data Step 2 — Train Step 3 — Evaluate Step 4 — Scale the data where it helps Step 5 — Deploy What we learned What you can build with it Get Started Introducing NVIDIA Nemotron 3.5 ASR , streaming multilingual: a 600M-parameter speech-to-text model that transcribes 40 language-locales from a single checkpoint , in real time , with punctuation and capitalization built in . It is the successor of the popular Nemotron 3 ASR model (English only) which was released on Hugging Face and as a NIM earlier this year. Since its release, Nemotron 3 ASR has been validated by independent benchmarks at Artificial Analysis, where it ranks 2nd in latency among all streaming ASR models — with just 0.07 seconds to final transcript after end of speech — and sits in the "most attractive quadrant" of the AA-WER Streaming Index vs. Time to Final Transcription leaderboard, placing it among the best models on the combined accuracy-latency tradeoff. The model uses a Cache-Aware FastConformer-RNNT architecture that streams audio without the redundant recomputation that makes most streaming ASR slow — so you get low latency and high accuracy, not one at the expense of the other.
Nemotron 3.5 ASR ships as open weights on Hugging Face — you can inspect, fine-tune, and deploy it without API dependencies or per-call billing. No data leaves your infrastructure unless you choose. And because it's a strong base model, you can fine-tune it for your own language, domain, or accent. The second half of this post walks through exactly how.
Source: https://huggingface.co/blog/nvidia/fine-tuning-nemotron-35-asr
Nemotron 3.5 ASR ships as open weights on Hugging Face — you can inspect, fine-tune, and deploy it without API dependencies or per-call billing. No data leaves your infrastructure unless you choose. And because it's a strong base model, you can fine-tune it for your own language, domain, or accent. The second half of this post walks through exactly how.
Source: https://huggingface.co/blog/nvidia/fine-tuning-nemotron-35-asr