Quantize Speech Recognition Models using NNCF PTQ API

This tutorial demonstrates how to apply INT8 quantization to the speech recognition models, using post-training quantization with NNCF (Neural Network Compression Framework).

The code of the tutorial is designed to be extendable to custom models and datasets.

Notebook Contents

The tutorial consists of the following steps:

Downloading and preparing the model and dataset.
Defining data loading and accuracy validation functionality.
Preparing the model for quantization.
Running quantization.
Comparing performance of the original and quantized models.
Compare accuracy of the original and quantized models.

Installation Instructions

This is a self-contained example that relies solely on its own code.
We recommend running the notebook in a virtual environment. You only need a Jupyter server to start. For details, please refer to Installation Guide.