Downloads · 30 days
16
18% of all-time downloads
medasr-onnx
ysdede/medasr-onnx
medasr-onnx is a automatic speech recognition model from ysdede. Use it when you need speech turned into text. It is set up for onnxruntime. The card lists the license as apache-2.0.
ONNX export assets for google/medasr: - model.onnx - model.onnx.data - tokens.txt - config.json - preprocessorconfig.json
All-time downloads
90
Public
Repo size
959 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data421 MB · 56%
At a glance
- Task
- Automatic Speech Recognition
- Library
- onnxruntime
- License
- apache-2.0
- Model type
- lasr_ctc
- Access
- Public
- Created
- Feb 22, 2026
- Updated
- Feb 22, 2026
- SHA
- 2baa5ece
Model card
From the Hugging Face model README
MedASR ONNX (ysdede)
ONNX export assets for google/medasr:
model.onnxmodel.onnx.datatokens.txtconfig.jsonpreprocessor_config.json
Browser usage (onnxruntime-web)
Use both:
- model URL:
https://huggingface.co/ysdede/medasr-onnx/resolve/main/model.onnx - model data URL:
https://huggingface.co/ysdede/medasr-onnx/resolve/main/model.onnx.data - tokens URL:
https://huggingface.co/ysdede/medasr-onnx/resolve/main/tokens.txt
If loading from bytes, pass externalData for model.onnx.data.
- Task
- Automatic Speech Recognition
- Library
- onnxruntime
- Type
- lasr_ctc
- License
- apache-2.0
- Created
- Feb 22, 2026
- Updated
- Feb 22, 2026