This repository was archived by the owner on Jun 19, 2025. It is now read-only.

mozilla / DeepSpeech Public archive

Notifications You must be signed in to change notification settings
Fork 4.1k
Star 26.6k

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.

License

MPL-2.0 license

26.6k stars 4.1k forks Branches Tags Activity

Star

Notifications

mozilla/DeepSpeech

Branches Tags

Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 3,467 Commits
.github		.github
bin		bin
ci_scripts		ci_scripts
data		data
doc		doc
examples		examples
images		images
kenlm @ 0c4dd4e		kenlm @ 0c4dd4e
native_client		native_client
taskcluster		taskcluster
tensorflow @ 23ad988		tensorflow @ 23ad988
tests		tests
training/deepspeech_training		training/deepspeech_training
.cardboardlint.yml		.cardboardlint.yml
.compute		.compute
.gitattributes		.gitattributes
.gitignore		.gitignore
.gitmodules		.gitmodules
.isort.cfg		.isort.cfg
.pylintrc		.pylintrc
.readthedocs.yml		.readthedocs.yml
BIBLIOGRAPHY.md		BIBLIOGRAPHY.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CODE_OWNERS.rst		CODE_OWNERS.rst
CONTRIBUTING.rst		CONTRIBUTING.rst
DeepSpeech.py		DeepSpeech.py
Dockerfile.build.tmpl		Dockerfile.build.tmpl
Dockerfile.train.tmpl		Dockerfile.train.tmpl
GRAPH_VERSION		GRAPH_VERSION
ISSUE_TEMPLATE.md		ISSUE_TEMPLATE.md
LICENSE		LICENSE
Makefile		Makefile
README.rst		README.rst
RELEASE.rst		RELEASE.rst
SUPPORT.rst		SUPPORT.rst
VERSION		VERSION
bazel.patch		bazel.patch
build-python-wheel.yml-DISABLED_ENABLE_ME_TO_REBUILD_DURING_PR		build-python-wheel.yml-DISABLED_ENABLE_ME_TO_REBUILD_DURING_PR
ds_generic.supp		ds_generic.supp
ds_lib.supp		ds_lib.supp
ds_openfst.supp		ds_openfst.supp
ds_sox.supp		ds_sox.supp
evaluate.py		evaluate.py
evaluate_tflite.py		evaluate_tflite.py
lm_optimizer.py		lm_optimizer.py
parse_valgrind_suppressions.sh		parse_valgrind_suppressions.sh
requirements_eval_tflite.txt		requirements_eval_tflite.txt
requirements_tests.txt		requirements_tests.txt
requirements_transcribe.txt		requirements_transcribe.txt
setup.py		setup.py
stats.py		stats.py
taskcluster.disabled.yml		taskcluster.disabled.yml
tensorflow_full_runtime.supp		tensorflow_full_runtime.supp
tensorflow_tflite_runtime.supp		tensorflow_tflite_runtime.supp
transcribe.py		transcribe.py

Repository files navigation

Status

This project is now discontinued.

Project DeepSpeech

Documentation macOS builds Linters 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. Project DeepSpeech uses Google's TensorFlow to make the implementation easier.

Documentation for installation, usage, and training models are available on deepspeech.readthedocs.io.

For the latest release, including pre-trained models and checkpoints, see the latest release on GitHub.

For contribution guidelines, see CONTRIBUTING.rst.

For contact and support information, see SUPPORT.rst.

About

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.