Model reference · open weights
nemotron-3.5-asr-streaming is an open-weight audio or speech model from handy-computer, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
nemotron-3.5-asr-streaming-0.6b: transcribe.cpp GGUF GGUF conversions of nvidia/nemotron-3.5-asr-streaming-0.6b for use with transcribe.cpp. Ported from upstream commit 24b151a, pinned 2026-06-08. Validated against the NeMo reference at transcribe.cpp commit 909e94e on 2026-06-08. Multilingual speech-to-text across 32 supported language-locales (the model's tokenizer recognizes 40, but 8 are adaptation-ready and need fine-tuning) with punctuation and capitalization. A 0.6B-parameter cache-aware streaming FastConformer encoder with a prompt-conditioned RNN-T transducer decoder; the target language is selected per call (--language en-US, fr-FR, de-DE, ...) and an auto mode emits a <lang-XX tag. Ships both the offline path (attcontextsize=[56, 13], 1.12s, headline accuracy) and runtime-selectable chunked streaming (--stream-chunk-ms 1120 --stream-att-right {0,3,6,13}). Downloads WER measured on FLEURS test en (647 utterances), greedy RNN-T, --language en-US, whisper-normalizer scoring; the per-quant column is FLEURS en. NeMo reference baseline on the same manifest: 7.99% (NVIDIA self-reports 7.91% en-US). On LibriSpeech test-clean (2620 utterances) the same presets score F32 3.04 / F16 3.03 / Q80 3.06 / Q6K 3.07 / Q5KM 3.10 / Q4KM 3.28, against a 3.03% NeMo reference. Usage Build transcribe.cpp from source: Run on a 16 kHz mono WAV: If your audio isn't already 16 kHz mono WAV, convert it first: See the transcribe.cpp model page for performance numbers, numerical validation, and reproduction steps. License Inherited from the base model: OpenMDW-1.1. See the upstream model card for full terms. Original Model Card The section below is reproduced from nvidia/nemotron-3.5-asr-streaming-0.6b at commit 24b151a for offline reference. The upstream card is the authoritative source. Nemotron 3.5 ASR h1, h2, h3, h4, h5, h6 { color: #76b900; / NVIDIA green / font-weight: 700; } hr { border: none; border-top: 1px solid #e5e7eb; margin: 2rem 0; } / Improve list spacing / ul, ol { margin-top: 0.5rem; margin-bottom: 0.5rem; } / Badge alignment consistency / img { display: inline; vertical-align: middle; } [!Note] This model is the multilingual extension of nvidia/nemo
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | handy-computer |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transcribe.cpp |
| Based on | nvidia/nemotron-3.5-asr-streaming-0.6b |
| Released | 2026-06-07 |
| Popularity | 1.9M downloads / month |
| Likes | 5 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| nemotron-3.5-asr-streaming-0.6b-gguf | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys nemotron-3-5-asr-streaming for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nemotron-3-5-asr-streaming below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="nemotron-3-5-asr-streaming" -F file=@audio.mp3
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗