OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Heartgpt

HeartGPT is a Python repository of pretrained transformer models for ECG and PPG time-series, with scripts and graphical interfaces for generation, fine-tuning and interpretability.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Heartgpt — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use HeartGPT when working with ECG or PPG data and you want a code-based starting point for signal generation, cardiac-task fine-tuning or model interpretation.

Who it is for

  • Researchers exploring generative models for cardiac signals.
  • Developers adapting pretrained ECG or PPG models to cardiac tasks.

Documented uses

  • Generate future ECG or PPG time-series from example signal contexts.
  • Fine-tune pretrained models for arrhythmia screening or heartbeat detection.
  • Inspect model behavior using attention maps and interpretability tools.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. It is Python-based and uses PyTorch.

  • The repository provides both pretrained checkpoints and fine-tuned models for arrhythmia and beat-detection tasks.
  • Generation uses example ECG or PPG contexts to predict future time steps.
  • The project includes CLI scripts and GUIs, but the provided documentation does not give a complete installation sequence.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Generate future ECG or PPG signal steps from example contexts

Use the described generation script and pretrained model files to generate future steps from an ECG or PPG context.

Before you start

  • A sample ECG or PPG context from Example_inputs/ or another context in the expected format.
  • The corresponding pretrained ECGPT or PPGPT model files.

Steps

  1. Choose an ECG or PPG example context from Example_inputs/.

  2. Use Heart_PT_generate.py to load the example context and the corresponding ECGPT or PPGPT model.

  3. Generate future time steps; the repository lists outputs/ as the default location for generated sequences.

Expected outcome

Future ECG or PPG time steps are generated from the chosen context, with `outputs/` identified as the default output location.

Guide limitations

  • The source does not provide execution commands, configuration details, or expected output formats.
  • The source describes generation with pretrained models but does not document a complete installation or environment setup.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
harryjdavies/HeartGPT · Official homepage title · retained in its source language
How we review sourcesSuggest a correction