Downloads · 30 days
14
21% of all-time downloads
nemo-voice-typing-asr
Garnet-Owl/nemo-voice-typing-asr
nemo-voice-typing-asr is a automatic speech recognition model from Garnet-Owl. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as other.
Streaming English ASR model from NVIDIA NeMo, exported to ONNX and quantised to INT4 for CPU inference. No GPU required.
All-time downloads
67
Public
Repo size
728 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.data723 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- other
- Model type
- nemotron-speech-streaming
- Access
- Public
- Created
- Jun 30, 2026
- Updated
- Sep 22, 2026
- SHA
- c5d3f9b1
Model card
From the Hugging Face model README
nemotron-speech-streaming-en-0.6b (ONNX, INT4)
Streaming English ASR model from NVIDIA NeMo, exported to ONNX and quantised to INT4 for CPU inference. No GPU required.
Originally packaged by Microsoft / GitHub Copilot under MIT. The underlying ASR weights are under the NVIDIA Open Model License, which permits modification and redistribution. The bundled Silero VAD is MIT.
What's in here
| File | Purpose |
|---|---|
encoder.onnx + encoder.onnx.data | Chunked transformer encoder, 24 layers x 1024 hidden |
decoder.onnx + decoder.onnx.data | 2-layer LSTM predictor, 640 hidden |
joint.onnx + joint.onnx.data | RNN-T joint network, vocab 1024 plus blank |
silero_vad.onnx | Voice activity detector |
vocab.txt / tokenizer.json | SentencePiece vocabulary (1025 tokens incl. blank) |
genai_config.json, model_config.json, audio_processor_config.json | Runtime configuration |
Audio pipeline
- 16 kHz mono PCM
- 128-bin log-mel features, n_fft=512, hop=160, window=400, Hann, preemphasis 0.97
- 560 ms chunks (8960 samples), 9-frame mel pre-encode cache
- Encoder produces 7 timesteps per chunk (subsampling factor 8)
- Greedy RNN-T decode with
max_symbols_per_step=10
System requirements
- Any modern x86-64 CPU with AVX2 (Windows, Linux, or macOS via ONNX Runtime)
- About 900 MB of RAM at runtime
- About 600 MB on disk
Desktop app
A ready-to-use Windows tray app that streams from your microphone into this model and types the result into the focused window: github.com/Garnet-Owl/nemo-voice-typing
Quickstart (Python)
import onnxruntime as ort
encoder = ort.InferenceSession("encoder.onnx")
decoder = ort.InferenceSession("decoder.onnx")
joint = ort.InferenceSession("joint.onnx")
# See genai_config.json for the per-session input shapes and cache layout.
- Task
- Automatic Speech Recognition
- Library
- onnx
- Type
- nemotron-speech-streaming
- License
- other
- Languages
- en
- Created
- Jun 30, 2026
- Updated
- Sep 22, 2026