Downloads · 30 days
0
nemotron-3.5-asr-streaming-0.6b-onnx-int4-c112-cpu
DimQ1/nemotron-3.5-asr-streaming-0.6b-onnx-int4-c112-cpu
nemotron-3.5-asr-streaming-0.6b-onnx-int4-c112-cpu is a machine learning model from DimQ1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
ONNX export of NVIDIA Nemotron-3.5 ASR streaming (0.6B), CPU execution provider.
Access
Public
Updated Aug 28, 2026
Repo size
793 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data788 MB · 99%
At a glance
- License
- other
- Access
- Public
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026
- SHA
- 86830432
Model card
From the Hugging Face model README
Nemotron 3.5 ASR · INT4 · 1.12s
ONNX export of NVIDIA Nemotron-3.5 ASR streaming (0.6B), CPU execution provider.
- Window: c112
- Precision: INT4
- left_context: 56 encoded frames (model training-time value)
- Notes: Recommended (best size/accuracy)
WER (Common Voice 17, 250 ru + 250 en, CPU)
19.21% (ru 15.72% / en 22.41%)
Contents
encoder.onnx(+ external data) — FastConformer cache-aware encoderdecoder.onnx(+ external data) — RNN-T LSTM prediction networkjoint.onnx(+ external data) — transducer jointgenai_config.json,audio_processor_config.json— ORT GenAI configtokenizer.json,tokenizer_config.json,vocab.txtsilero_vad.onnx
License
See the original NVIDIA Nemotron license.
- License
- other
- Languages
- ru, en
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026