mohitsha/whisper-tiny-static-shape-quantized-SL-448
By mohitsha · ↓ 2 · ♥ 0 · Updated 2023-10-24
What's in this repo
This page lists the files in mohitsha/whisper-tiny-static-shape-quantized-SL-448, including decoder_model_quantized.onnx, decoder_model_quantized_static_scatter.onnx, encoder_model.onnx and more.
- 4 ONNX models (.onnx files)
- 17 files, including 9 .json, 4 .onnx, 1 .md, 1 .txt, 1 .py
- Last updated 2023-10-24
ONNX files
| File | Size | Download |
|---|---|---|
| decoder_model_quantized.onnx | — | Download |
| decoder_model_quantized_static_scatter.onnx | — | Download |
| encoder_model.onnx | — | Download |
| sq_model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Whisper Model Quantized
The repository contains the whisper model quantized using the Smooth Quant using ONNXRuntime
- Only the Whisper decoder is quantized in the model
- The model has been modified to accept fixed shapes input of (1, 80, 3000) for the encoder and (1,448) for decoder.
- For inference the un-quantized encoder model and quantized decoder model is used.
- This model is for testing and could be modified in the future with better versions.
Evaluation:
The model achieves WER of 6.02% on the librispeech_asr (clean) test dataset
Model info
Created: 2023-10-06
Updated: 2023-10-24
View on Hugging Face