π§
Nemotron 3.5 Asr Streaming 0.6b model by nvidia
β 62.7
π¬Technical Deep Dive
Full Specifications [+]
π Updated daily
Source summary: Based on Hugging Face metadata. Not a recommendation.
π‘οΈ Model Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
π Identity & Source
- id
- hf-model--nvidia--nemotron-3.5-asr-streaming-0.6b
- slug
- nvidia--nemotron-3.5-asr-streaming-0.6b
- source
- huggingface
- author
- nvidia
- license
- Other
- tags
- nemo, safetensors, nemotron3_5_asr, feature-extraction, transformers, speech-recognition, cache-aware asr, automatic-speech-recognition, streaming-asr, multilingual, speech, audio, fastconformer, rnnt, parakeet, asr, pytorch, en, es, de, fr, it, ar, ja, ko, pt, ru, hi, zh, vi, he, nl, cs, da, pl, no, sv, th, tr, bg, el, et, fi, hr, hu, lt, lv, ro, sk, uk, mt, sl, dataset:nvidia/granary, dataset:multilingual_librispeech, dataset:fleurs, dataset:mozilla-foundation/common_voice_8_0, dataset:voxpopu
βοΈ Technical Specs
- architecture
- Nemotron3_5AsrForRNNT
- params billions
- 0.64
- context length
- 8,192
- pipeline tag
- automatic-speech-recognition
- vram gb
- 1.8
- vram is estimated
- true
- vram formula
- VRAM β (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)
π Engagement & Metrics
- downloads
- 590,230
- stars
- null
- forks
- null
Data indexed from public sources. Updated daily.