DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
26,781
stars
2,727
commits
C++
primary language
Jun 19, 2025
updated
deep-learning
deepspeech
embedded
machine-learning
neural-networks
offline
on-device
speech-recognition
speech-to-text
tensorflow
README
Status ====== This project is now discontinued. Project DeepSpeech ================== .. image:: https://readthedocs.org/projects/deepspeech/badge/?version=latest :target: https://deepspeech.readthedocs.io/?badge=latest :alt: Documentation .. image:: https://github.com/mozilla/DeepSpeech/actions/workflows/macOS-amd64.yml/badge.svg :target: https://github.com/mozilla/DeepSpeech/actions/workflows/macOS-amd64.yml :alt: macOS builds .. image:: https://github.com/mozilla/DeepSpeech/actions/workflows/lint.yml/badge.svg :target: https://github.com/mozilla/DeepSpeech/actions/workflows/lint.yml :alt: Linters .. image:: https://github.com/mozilla/DeepSpeech/actions/workflows/docker.yml/badge.svg :target: https://github.com/mozilla/DeepSpeech/actions/workflows/docker.yml :alt: Docker Images DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on `Baidu's Deep Speech research paper <https://arxiv.org/abs/1412.5567>`_. Project DeepSpeech uses Google's `TensorFlow <https://www.tensorflow.org/>`_ to make the implementation easier. Documentation for installation, usage, and training models are available on `deepspeech.readthedocs.io <https://deepspeech.readthedocs.io/?badge=latest>`_. For the latest release, including pre-trained models and checkpoints, `see the latest release on GitHub <https://github.com/mozilla/DeepSpeech/releases/latest>`_. For contribution guidelines, see `CONTRIBUTING.rst <CONTRIBUTING.rst>`_. For contact and support information, see `SUPPORT.rst <SUPPORT.rst>`_.
Not written in Markdown, so it's shown here as plain text — view it formatted on GitHub.
Contributors
(top 30 of 129)
Similar repos
Languages
C++
47.0%
Python
21.4%
C
11.2%
Shell
10.8%
C#
2.8%
Swift
1.8%
Java
1.3%
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
26,781
stars
2,727
commits
C++
primary language
Jun 19, 2025
updated
deep-learning
deepspeech
embedded
machine-learning
neural-networks
offline
on-device
speech-recognition
speech-to-text
tensorflow
README
Status ====== This project is now discontinued. Project DeepSpeech ================== .. image:: https://readthedocs.org/projects/deepspeech/badge/?version=latest :target: https://deepspeech.readthedocs.io/?badge=latest :alt: Documentation .. image:: https://github.com/mozilla/DeepSpeech/actions/workflows/macOS-amd64.yml/badge.svg :target: https://github.com/mozilla/DeepSpeech/actions/workflows/macOS-amd64.yml :alt: macOS builds .. image:: https://github.com/mozilla/DeepSpeech/actions/workflows/lint.yml/badge.svg :target: https://github.com/mozilla/DeepSpeech/actions/workflows/lint.yml :alt: Linters .. image:: https://github.com/mozilla/DeepSpeech/actions/workflows/docker.yml/badge.svg :target: https://github.com/mozilla/DeepSpeech/actions/workflows/docker.yml :alt: Docker Images DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on `Baidu's Deep Speech research paper <https://arxiv.org/abs/1412.5567>`_. Project DeepSpeech uses Google's `TensorFlow <https://www.tensorflow.org/>`_ to make the implementation easier. Documentation for installation, usage, and training models are available on `deepspeech.readthedocs.io <https://deepspeech.readthedocs.io/?badge=latest>`_. For the latest release, including pre-trained models and checkpoints, `see the latest release on GitHub <https://github.com/mozilla/DeepSpeech/releases/latest>`_. For contribution guidelines, see `CONTRIBUTING.rst <CONTRIBUTING.rst>`_. For contact and support information, see `SUPPORT.rst <SUPPORT.rst>`_.
Not written in Markdown, so it's shown here as plain text — view it formatted on GitHub.
Similar repos
Contributors
(top 30 of 129)
Languages
C++
47.0%
Python
21.4%
C
11.2%
Shell
10.8%
C#
2.8%
Swift
1.8%
Java
1.3%