STT/ASR - onnx
Collection
OVOS STT/ASR models for onnx-asr (ONNX runtime). Most ship fp32 + int8 (set quantization: int8 for faster/smaller CPU inference). • 233 items • Updated • 2
Moonshine Base (ONNX)
Moonshine Base is a compact English speech-to-text model from Useful Sensors. It is an encoder-decoder model that reads the raw 16 kHz waveform, so it needs no log-mel preprocessor.
This repository is a mirror of the official ONNX export onnx-community/moonshine-base-ONNX, kept so that the OpenVoiceOS ONNX ASR collection is self-contained. The weights are unchanged.
Usage
import onnx_asr
model = onnx_asr.load_model("moonshine-base")
print(model.recognize("test.wav"))
Quantized variants load with the quantization argument:
model = onnx_asr.load_model("moonshine-base", quantization="quantized")
Credits
Model by Useful Sensors Inc., released under the MIT license. Paper: Moonshine: Speech Recognition for Live Transcription and Voice Commands. ONNX export by onnx-community.
License
MIT
- Downloads last month
- 20
Model tree for OpenVoiceOS/moonshine-base-onnx
Base model
moonshine-ai/moonshine-base