mirror of
https://github.com/mozilla/DeepSpeech.git
synced 2025-10-26 11:19:39 +00:00
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.
deep-learningdeepspeechembeddedmachine-learningneural-networksofflineon-devicespeech-recognitionspeech-to-texttensorflow
64e9dd6bb1
This is a convenience change for manually iterating on tasks in the TaskCluster UI. The "edit task" UI removes the tasks' dependencies, which means when editing a test task you need to manually reinsert the dependencies every time. This separates the dependency for scheduling purposes from the dependency for downloading artifacts, so that the latter is kept in the "edit task" UI and one can just edit the payload as needed to develop/debug/iterate. |
||
|---|---|---|
| .circleci | ||
| .github | ||
| bin | ||
| data | ||
| doc | ||
| examples | ||
| images | ||
| kenlm@689a25aae9 | ||
| native_client | ||
| taskcluster | ||
| tensorflow@23ad988fcd | ||
| tests | ||
| training/deepspeech_training | ||
| util | ||
| .cardboardlint.yml | ||
| .compute | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| .isort.cfg | ||
| .pylintrc | ||
| .readthedocs.yml | ||
| .taskcluster.yml | ||
| bazel.patch | ||
| BIBLIOGRAPHY.md | ||
| build-python-wheel.yml-DISABLED_ENABLE_ME_TO_REBUILD_DURING_PR | ||
| CODE_OF_CONDUCT.md | ||
| CODE_OWNERS.rst | ||
| CONTRIBUTING.rst | ||
| DeepSpeech.py | ||
| Dockerfile.build.tmpl | ||
| Dockerfile.train.tmpl | ||
| ds_generic.supp | ||
| ds_lib.supp | ||
| ds_openfst.supp | ||
| ds_sox.supp | ||
| evaluate_tflite.py | ||
| evaluate.py | ||
| GRAPH_VERSION | ||
| ISSUE_TEMPLATE.md | ||
| LICENSE | ||
| lm_optimizer.py | ||
| Makefile | ||
| parse_valgrind_suppressions.sh | ||
| README.rst | ||
| RELEASE.rst | ||
| requirements_eval_tflite.txt | ||
| requirements_tests.txt | ||
| requirements_transcribe.txt | ||
| setup.py | ||
| stats.py | ||
| SUPPORT.rst | ||
| tensorflow_full_runtime.supp | ||
| tensorflow_tflite_runtime.supp | ||
| transcribe.py | ||
| VERSION | ||
Project DeepSpeech ================== .. image:: https://readthedocs.org/projects/deepspeech/badge/?version=latest :target: https://deepspeech.readthedocs.io/?badge=latest :alt: Documentation .. image:: https://community-tc.services.mozilla.com/api/github/v1/repository/mozilla/DeepSpeech/master/badge.svg :target: https://community-tc.services.mozilla.com/api/github/v1/repository/mozilla/DeepSpeech/master/latest :alt: Task Status 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>`_.