Full-precision FP32 ONNX model converted from
NVIDIA Nemotron 3.5 ASR Streaming 0.6B using Microsoft Olive.
Maximum quality for CPU inference with
ONNX Runtime GenAI. No quantization — pure FP32 weights.
1using NemotronSpeech;
2
3using var session = new ModelSession(
4 modelPath: "DimQ1/nemotron-3.5-asr-streaming-0.6b-onnx-fp32-cpu",
5 executionProvider: "cpu",
6 langId: "11", // Russian
7 useVad: true
8);
1import onnxruntime_genai as og
2
3model = og.Model("DimQ1/nemotron-3.5-asr-streaming-0.6b-onnx-fp32-cpu")
4processor = og.StreamingProcessor(model)
5# ...
