# compressionKIT

## What is compressionKIT?

compressionKIT is a Python development kit for compressing ECG and PPG waveforms. It brings codec models, signal preprocessing, evaluation and export into one workflow, so you can compare approaches before preparing an application for the edge.

A codec encodes a frame of samples into a smaller representation and decodes it back into a waveform. Compression can change the reconstructed signal. The [evidence pages](https://ambiqai.github.io/compressionkit/customer-evidence/) help you inspect that tradeoff alongside payload size, rather than relying on compression ratio alone.

## What you can do

- [Retain waveform recordings](https://ambiqai.github.io/compressionkit/use-cases/)Explore smaller payloads for storage and transfer, while checking the quality of the reconstructed signal.Explore use cases →

- [Compare quality and size](https://ambiqai.github.io/compressionkit/customer-evidence/)Inspect waveform and physiological measures across PPG and ECG configurations.Review the evidence →

- [Prepare deployment artifacts](https://ambiqai.github.io/compressionkit/deployment/)Export models, codebooks, manifests and reference vectors for integration work.Explore deployment →

- [Build on reusable components](https://ambiqai.github.io/compressionkit/experiment-architecture/)Use a provided experiment or compose your own workflow from the available blocks.Build your own workflow →

## Installation

Use Python 3.12 and a source checkout to get started:

```bash
git clone https://github.com/AmbiqAI/compressionkit.git
cd compressionkit
uv sync --python 3.12 --extra hf
```

The `hf` extra supports loading remote Hugging Face bundles. The [Getting Started guide](https://ambiqai.github.io/compressionkit/getting-started/) runs a first encode/decode example; no training dataset is needed for that path.

## Explore the documentation

- [Getting started](https://ambiqai.github.io/compressionkit/getting-started/)Install compressionKIT and run your first encode/decode example.Start here →

- [Hugging Face bundles](https://ambiqai.github.io/compressionkit/huggingface/)Load a remote bundle or an existing local deploy directory.Load a codec →

- [Model zoo](https://ambiqai.github.io/compressionkit/models/)Review signal-specific results, configurations and reconstruction plots.Browse models →

- [Reproducible experiments](https://ambiqai.github.io/compressionkit/experiments/)Find a registered configuration, prepare its dataset and run the workflow.Explore experiments →