Instructions to use mohitsha/whisper-tiny-dynamic-quantized-onnxruntime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mohitsha/whisper-tiny-dynamic-quantized-onnxruntime with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mohitsha/whisper-tiny-dynamic-quantized-onnxruntime")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mohitsha/whisper-tiny-dynamic-quantized-onnxruntime") model = AutoModelForSpeechSeq2Seq.from_pretrained("mohitsha/whisper-tiny-dynamic-quantized-onnxruntime", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download decoder_with_past_model_quantized.onnx from mohitsha/whisper-tiny-dynamic-quantized-onnxruntime: direct link, hf CLI and curl.
- Browser
- Download file 49.1 MB
-
https://huggingface.co/mohitsha/whisper-tiny-dynamic-quantized-onnxruntime/resolve/main/decoder_with_past_model_quantized.onnx
- Command line
-
hf download hf://mohitsha/whisper-tiny-dynamic-quantized-onnxruntime/decoder_with_past_model_quantized.onnx
-
curl -L -o decoder_with_past_model_quantized.onnx https://huggingface.co/mohitsha/whisper-tiny-dynamic-quantized-onnxruntime/resolve/main/decoder_with_past_model_quantized.onnx
49.1 MB
- Xet hash:
- 2f6f32ac072bd6108e8cb80bcd39e323f05fa37222452087acf32124be4d7275
- Size of remote file:
- 49.1 MB
- SHA256:
- 049bd9539b176a717ede870e4fdfdbfa0d777342e95e9aa28f9dd67801ef68a4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.