{"v":1,"id":"model:hf:nvidia/nemotron-3.5-asr-streaming-0.6b","slug":"model-nvidia-nemotron-3-5-asr-streaming-0-6b","kind":"model","category":"speech","title":"nemotron-3.5-asr-streaming-0.6b","summary":"This model is the multilingual extension of nvidia/nemotron-speech-streaming-en-0.6b, adding language-ID prompt conditioning to support transcription across 40 language-locales from a single model.","source":{"provider":"hf","ref":"nvidia/nemotron-3.5-asr-streaming-0.6b","url":"https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b","rev":"ea30d66debe3740a08b573244286791d423d6b3e","fetchedAt":"2026-10-02T20:54:17.963Z","etag":"W/\"3069-o0CAvkXCE2R58wxzkSFf2dFpu1I\""},"author":{"name":"nvidia","url":"https://huggingface.co/nvidia"},"license":{"spdx":null,"raw":"other","url":"https://openmdw.ai/license/1-1/","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":1240287,"likes":1159,"stars":18539,"openIssues":325,"lastRelease":{"tag":"v3.0.0","at":"2026-08-07T00:13:21Z"},"pushedAt":"2026-10-02T16:11:38Z","takenAt":"2026-10-02T20:54:17.963Z"},"tags":["nemo","safetensors","gguf","nemotron3_5_asr","feature-extraction","transformers","speech-recognition","cache-aware ASR","automatic-speech-recognition","streaming-asr","multilingual","speech","audio","FastConformer","RNNT","Parakeet","ASR","pytorch","NeMo","en","es","de","fr","it","ar","ja","ko","pt","ru","hi","zh","vi","he","nl","cs","da","pl","no","sv","th"],"pipeline":"automatic-speech-recognition","links":{"github":"NVIDIA-NeMo/Speech"},"updatedAt":"2026-09-10T16:49:07.000Z","collectedAt":"2026-10-02T20:54:17.963Z","review":{"numbers":["1,240,287 downloads on Hugging Face","1,159 likes","license other","0.7 GB for nemotron-3.5-asr-streaming-0.6b.q8_0.gguf","18,539 stars on NVIDIA-NeMo/Speech","325 open issues and PRs","last release v3.0.0 on 2026-08-07"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:54:17.963Z","http":200},"description":"# Nemotron 3.5 ASR\n\nh1, h2, h3, h4, h5, h6 {\n  color: #76b900; /* NVIDIA green */\n  font-weight: 700;\n}\n\nhr {\n  border: none;\n  border-top: 1px solid #e5e7eb;\n  margin: 2rem 0;\n}\n\n/* Improve list spacing */\nul, ol {\n  margin-top: 0.5rem;\n  margin-bottom: 0.5rem;\n}\n\n/* Badge alignment consistency */\nimg {\n  display: inline;\n  vertical-align: middle;\n}\n\n  \n    \n  \n   \n  \n    \n  \n   \n  \n    \n  \n  \n    \n  \n\n    \n  \n  \n    \n  \n\n  \n\n  \n\n> [!Note]\n> This model is the multilingual extension of [nvidia/nemotron-speech-streaming-en-0.6b](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b), adding language-ID prompt conditioning to support transcription across **40 language-locales** from a single model.\n\n**Nemotron 3.5 ASR** is a multilingual, streaming Automatic Speech Recognition (ASR) model engineered to deliver high-quality multilingual transcription across both low-latency streaming and high-throughput batch workloads. Developed by NVIDIA, this 600M parameter model transcribes speech into text with native support for punctuation and capitalization, and offers runtime flexibility with configurable chunk sizes, including 80ms, 160ms, 320ms, 560ms, and 1120ms.\n\nBy leveraging a state-of-the-art **Cache-Aware FastConformer-RNNT** architecture, the model eliminates redundant overlapping computations common in traditional \"buffered\" streaming. This allows it to process only new audio chunks while reusing cached encoder context, significantly improving computational efficiency and minimizing end-to-end delay without sacrificing accuracy.\n\nIt was trained on a massive ASR dataset and is engineered to perform across diverse and challenging acoustic conditions.\n\nThis model is ready for commercial use.\n\n## Release Date\n\n- Hugging Face [06/04/2026] via https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b\n\n## Why Choose Nemotron 3.5 ASR?\n\n- 🌍 **Single Multilingual Model:** Transcrib…\n\nSource: https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b","install":{"kind":"model","hfId":"nvidia/nemotron-3.5-asr-streaming-0.6b","gated":false,"format":"gguf","files":[{"name":"model.safetensors","size":2552062944,"sha256":"9eebdd6590289cb3030f310858f3df93256600a800a3e8200c5993d5f967e174"},{"name":"nemotron-3.5-asr-streaming-0.6b.q8_0.gguf","size":742090464,"quant":"Q8_0","sha256":"3fc991d3badad7277c11030a7519832cddaf2057aafed6d4b25147e953a070b1"}],"totalBytes":3294153408,"suggestedFile":"nemotron-3.5-asr-streaming-0.6b.q8_0.gguf","requirements":{"ramGb":2,"diskBytes":742090464,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"],"command":"lsh models install hf:nvidia/nemotron-3.5-asr-streaming-0.6b"}}