{"id":15136501,"url":"https://github.com/rhysdg/whisper-onnx-python","last_synced_at":"2026-02-16T20:10:00.909Z","repository":{"id":245925615,"uuid":"819550661","full_name":"rhysdg/whisper-onnx-python","owner":"rhysdg","description":"A  low-footprint GPU accelerated  Speech to Text Python package for the Jetpack 5 era bolstered by an optimized graph","archived":false,"fork":false,"pushed_at":"2024-06-30T21:50:30.000Z","size":3844,"stargazers_count":1,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-21T08:48:04.050Z","etag":null,"topics":["ai","chatbot","cuda","machine-learning","onnxruntime","speech-to-text","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rhysdg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-24T18:26:50.000Z","updated_at":"2024-07-19T19:01:05.000Z","dependencies_parsed_at":"2024-06-27T02:27:09.671Z","dependency_job_id":"dbeec349-2e49-4a37-9b44-4500c14c3d9a","html_url":"https://github.com/rhysdg/whisper-onnx-python","commit_stats":null,"previous_names":["rhysdg/whisper-onnx-python"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rhysdg/whisper-onnx-python","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhysdg%2Fwhisper-onnx-python","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhysdg%2Fwhisper-onnx-python/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhysdg%2Fwhisper-onnx-python/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhysdg%2Fwhisper-onnx-python/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rhysdg","download_url":"https://codeload.github.com/rhysdg/whisper-onnx-python/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rhysdg%2Fwhisper-onnx-python/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279012681,"owners_count":26085159,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-12T02:00:06.719Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","chatbot","cuda","machine-learning","onnxruntime","speech-to-text","whisper"],"created_at":"2024-09-26T06:22:13.717Z","updated_at":"2025-10-12T19:45:19.004Z","avatar_url":"https://github.com/rhysdg.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003c!-- PROJECT SHIELDS --\u003e\n[![Contributors][contributors-shield]](https://github.com/rhysdg/whisper-onnx-python/contributors)\n[![Apache][license-shield]][license-url]\n[![LinkedIn][linkedin-shield]][linkedin-url]\n\n\u003c!-- PROJECT LOGO --\u003e\n\u003cbr /\u003e\n  \u003ch3 align=\"center\"\u003e Whisper ONNX: An Optimized Speech-to-Text Python Package\u003c/h2\u003e\n  \u003cp align=\"center\"\u003e\n     \u003cbr /\u003e\n    \u003ca href=\"https://github.com/rhysdg/whisper-onnx-python/wiki\"\u003cstrong\u003eExplore the docs »\u003c/strong\u003e\u003c/a\u003e\n    \u003cbr /\u003e\n    \u003cbr /\u003e\n    \u003cimg src=\"data/whisper-onnx.png\" align=\"middle\" width=200\u003e\n    \u003cbr /\u003e\n    \u003cbr /\u003e\n    \u003ca href=\"https://github.com/rhysdg/whisper-onnx-python/issues\"\u003eReport Bug\u003c/a\u003e\n    .\n    \u003ca href=\"https://github.com/rhysdg/whisper-onnx-python/issues\"\u003eRequest Feature\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/p\u003e\n\n\u003c!-- TABLE OF CONTENTS --\u003e\n## Table of Contents\n\n* [About the Project](#about-the-project)\n  * [Built With](#built-with)\n  * [The Story so Far](#the-story-so-far)\n* [Getting Started](#getting-started)\n  * [Prerequisites](#prerequisites)\n  * [Scripts and Tools](#scripts-and-tools)\n  * [Supplementary Data](#supplementary-data)\n* [Proposed Updates](#proposed-updates)\n* [Contact](#contact)\n\n\u003c!-- ABOUT THE PROJECT --\u003e\n## About The Project\n\n### Built With\n\n* [Onnxruntime](https://onnxruntime.ai/)\n\n\n### The Story So Far\n\n**Coming soon**\n\n\n\n\u003c!-- GETTING STARTED --\u003e\n## Getting Started:\n\n- Right now getting started is as simple as either a pip install from root or the upstream repo:\n\n\n  ```bash\n  pip install .\n\n  #or \n\n  pip install git+https://github.com/rhysdg/whisper-onnx-python.git\n\n  ```\n\n- For Jetpack 5 support with Python 3.11 go ahead and run the installation script first to grab a pre-built `onnxruntime-gpu` wheel for `aarch_64` and a few extra dependencies:\n\n  ```bash\n  sh jetson_install.sh \n\n  pip install .\n\n  ```\n\n\n\n## Example usage:\n\n- Currently usage closely follows the official package but with a trt swicth (currently being debugged, False is recommended as a result) and expects either an audio file or a numy array:\n\n\n\n  ```python\n  import numpy as np\n  import whisper\n\n  args = {\"language\": 'English',\n          \"name\": \"small.en\",\n          \"precision\": \"fp32\",\n          \"disable_cupy\": False}\n\n  temperature = tuple(np.arange(0, 1.0 + 1e-6, 0.2))\n\n  model = whisper.load_model(trt=False, **args)\n  result = model.transcribe(\n                      'data/test.wav', \n                      temperature=temperature,\n                      **args\n                      )\n    ```\n\n- You can also find an example voice transcription assistant at `examples/example_assistant.py`\n\n  - Go ahead and hold in your space bar from the command line in order to start recording\n  - Release to  start transcription\n  - This has been tested on Ubuntu 22.04 and Jetpack 5 on a AGX  Xavier but feel free to open an issue so we can work through any issues!\n\n\n  ```bash\n  python examples/example_assistant.py\n  ```\n\n\n## Customisation:\n\n- **Coming soon**\n\n\n### Notebooks\n \n- **Coming soon**\n\n### Tools and Scripts\n-  **Coming soon**\n\n\n### Testing\n\n- Ubuntu 22.04 - RTX 3080, 8-core, Python 3.11 - **passing**\n- AGX Xavier, Jetpack 5.1.3, Python 3.11 - **Passing**\n\n - CI/CD will be expanded as we go - all general instantiation test pass so far.\n\n### Models \u0026 Latency benchmarks\n\n\n- **Coming soon**\n\n\n### Similar projects\n\n- Inspired by the work over at:\n  - [whisper-onnx-tensorrt](https://github.com/PINTO0309/whisper-onnx-tensorrt)\n  - [The original implementation](https://github.com/openai/whisper)\n\n\u003c!-- PROPOSED UPDATES --\u003e\n## Latest Updates\n- Finished the core Python package\n- Added an example assistant\n- Added Jetpack support\n\n\u003c!-- PROPOSED UPDATES --\u003e\n## Future updates\n\n- CI/CD\n- Pypi release\n- Becnhmarks for Jetson devices\n\n\u003c!-- Contact --\u003e\n## Contact\n- Project link: https://github.com/rhysdg/whisper-onnx-python\n- Email: [Rhys](rhysdgwilliams@gmail.com)\n\n\n\u003c!-- MARKDOWN LINKS \u0026 IMAGES --\u003e\n[build-shield]: https://img.shields.io/badge/build-passing-brightgreen.svg?style=flat-square\n[contributors-shield]: https://img.shields.io/badge/contributors-2-orange\n[license-shield]: https://img.shields.io/badge/License-GNU%20GPL-blue\n[license-url]: LICENSE.txt\n[linkedin-shield]: https://img.shields.io/badge/-LinkedIn-black.svg?style=flat-square\u0026logo=linkedin\u0026colorB=555\n[linkedin-url]: https://www.linkedin.com/in/rhys-williams-b19472160/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frhysdg%2Fwhisper-onnx-python","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frhysdg%2Fwhisper-onnx-python","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frhysdg%2Fwhisper-onnx-python/lists"}