You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Mozilla Voice STT 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>`_. Mozilla Voice STT uses Google's `TensorFlow <https://www.tensorflow.org/>`_ to make the implementation easier.
16
16
17
17
Documentation for installation, usage, and training models are available on `deepspeech.readthedocs.io <http://deepspeech.readthedocs.io/?badge=latest>`_.
18
18
19
-
For the latest release, including pre-trained models and checkpoints, `see the latest release on GitHub <https://github.com/mozilla/STT/releases/latest>`_.
19
+
For the latest release, including pre-trained models and checkpoints, `see the latest release on GitHub <https://github.com/mozilla/DeepSpeech/releases/latest>`_.
20
20
21
21
For contribution guidelines, see `CONTRIBUTING.rst <CONTRIBUTING.rst>`_.
Copy file name to clipboardexpand all lines: SUPPORT.rst
+3-3
Original file line number
Diff line number
Diff line change
@@ -5,8 +5,8 @@ Contact/Getting Help
5
5
6
6
There are several ways to contact us or to get help:
7
7
8
-
#. `Discourse Forums <https://discourse.mozilla.org/c/mozilla-voice-stt>`_ - The `Deep Speech category on Discourse <https://discourse.mozilla.org/c/mozilla-voice-stt>`_ is the first place to look. Search for keywords related to your question or problem to see if someone else has run into it already. If you can't find anything relevant there, search on our `issue tracker <https://github.com/mozilla/STT/issues>`_ to see if there is an existing issue about your problem.
8
+
#. `Discourse Forums <https://discourse.mozilla.org/c/deep-speech>`_ - The `Deep Speech category on Discourse <https://discourse.mozilla.org/c/deep-speech>`_ is the first place to look. Search for keywords related to your question or problem to see if someone else has run into it already. If you can't find anything relevant there, search on our `issue tracker <https://github.com/mozilla/deepspeech/issues>`_ to see if there is an existing issue about your problem.
9
9
10
-
#. `Matrix chat <https://chat.mozilla.org/#/room/#machinelearning:mozilla.org>`_ - If your question is not addressed by either the `FAQ <https://github.com/mozilla/STT/wiki#frequently-asked-questions>`_ or `Discourse Forums <https://discourse.mozilla.org/c/mozilla-voice-stt>`_\ , you can contact us on the ``#machinelearning`` channel on `Mozilla Matrix <https://chat.mozilla.org/#/room/#machinelearning:mozilla.org>`_\ ; people there can try to answer/help
10
+
#. `Matrix chat <https://chat.mozilla.org/#/room/#machinelearning:mozilla.org>`_ - If your question is not addressed by either the `FAQ <https://github.com/mozilla/DeepSpeech/wiki#frequently-asked-questions>`_ or `Discourse Forums <https://discourse.mozilla.org/c/deep-speech>`_\ , you can contact us on the ``#machinelearning`` channel on `Mozilla Matrix <https://chat.mozilla.org/#/room/#machinelearning:mozilla.org>`_\ ; people there can try to answer/help
11
11
12
-
#. `Create a new issue <https://github.com/mozilla/STT/issues>`_ - Finally, if you have a bug report or a feature request that isn't already covered by an existing issue, please open an issue in our repo and fill the appropriate information on your hardware and software setup.
12
+
#. `Create a new issue <https://github.com/mozilla/deepspeech/issues>`_ - Finally, if you have a bug report or a feature request that isn't already covered by an existing issue, please open an issue in our repo and fill the appropriate information on your hardware and software setup.
Copy file name to clipboardexpand all lines: doc/Decoder.rst
+1-1
Original file line number
Diff line number
Diff line change
@@ -22,7 +22,7 @@ The use of an external scorer is fully optional. When an external scorer is not
22
22
23
23
Currently, the Mozilla Voice STT external scorer is implemented with `KenLM <https://kheafield.com/code/kenlm/>`_, plus some tooling to package the necessary files and metadata into a single ``.scorer`` package. The tooling lives in ``data/lm/``. The scripts included in ``data/lm/`` can be used and modified to build your own language model based on your particular use case or language. See :ref:`scorer-scripts` for more details on how to reproduce our scorer file as well as create your own.
24
24
25
-
The scripts are geared towards replicating the language model files we release as part of `Mozilla Voice STT model releases <https://github.com/mozilla/STT/releases/latest>`_, but modifying them to use different datasets or language model construction parameters should be simple.
25
+
The scripts are geared towards replicating the language model files we release as part of `Mozilla Voice STT model releases <https://github.com/mozilla/DeepSpeech/releases/latest>`_, but modifying them to use different datasets or language model construction parameters should be simple.
Copy file name to clipboardexpand all lines: doc/Scorer.rst
+2-2
Original file line number
Diff line number
Diff line change
@@ -7,7 +7,7 @@ Mozilla Voice STT pre-trained models include an external scorer. This document e
7
7
8
8
The scorer is composed of two sub-components, a KenLM language model and a trie data structure containing all words in the vocabulary. In order to create the scorer package, first we must create a KenLM language model (using ``data/lm/generate_lm.py``, and then use ``generate_scorer_package`` to create the final package file including the trie data structure.
9
9
10
-
The ``generate_scorer_package`` binary is part of the native client package that is included with official releases. You can find the appropriate archive for your platform in the `GitHub release downloads <https://github.com/mozilla/STT/releases/latest>`_. The native client package is named ``native_client.{arch}.{config}.{plat}.tar.xz``, where ``{arch}`` is the architecture the binary was built for, for example ``amd64`` or ``arm64``, ``config`` is the build configuration, which for building decoder packages does not matter, and ``{plat}`` is the platform the binary was built-for, for example ``linux`` or ``osx``. If you wanted to run the ``generate_scorer_package`` binary on a Linux desktop, you would download ``native_client.amd64.cpu.linux.tar.xz``.
10
+
The ``generate_scorer_package`` binary is part of the native client package that is included with official releases. You can find the appropriate archive for your platform in the `GitHub release downloads <https://github.com/mozilla/DeepSpeech/releases/latest>`_. The native client package is named ``native_client.{arch}.{config}.{plat}.tar.xz``, where ``{arch}`` is the architecture the binary was built for, for example ``amd64`` or ``arm64``, ``config`` is the build configuration, which for building decoder packages does not matter, and ``{plat}`` is the platform the binary was built-for, for example ``linux`` or ``osx``. If you wanted to run the ``generate_scorer_package`` binary on a Linux desktop, you would download ``native_client.amd64.cpu.linux.tar.xz``.
11
11
12
12
Reproducing our external scorer
13
13
-------------------------------
@@ -44,7 +44,7 @@ Afterwards you can use ``generate_scorer_package`` to generate the scorer packag
44
44
45
45
cd data/lm
46
46
# Download and extract appropriate native_client package:
Copy file name to clipboardexpand all lines: doc/USING.rst
+8-8
Original file line number
Diff line number
Diff line change
@@ -33,12 +33,12 @@ The CUDA capable builds (Python, NodeJS, C++, etc) depend on CUDA 10.1 and CuDNN
33
33
Getting the pre-trained model
34
34
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
35
35
36
-
If you want to use the pre-trained English model for performing speech-to-text, you can download it (along with other important inference material) from the Mozilla Voice STT `releases page <https://github.com/mozilla/STT/releases>`_. Alternatively, you can run the following command to download the model files in your current directory:
36
+
If you want to use the pre-trained English model for performing speech-to-text, you can download it (along with other important inference material) from the Mozilla Voice STT `releases page <https://github.com/mozilla/DeepSpeech/releases>`_. Alternatively, you can run the following command to download the model files in your current directory:
There are several pre-trained model files available in official releases. Files ending in ``.pbmm`` are compatible with clients and language bindings built against the standard TensorFlow runtime. Usually these packages are simply called ``mozilla_voice_stt``. These files are also compatible with CUDA enabled clients and language bindings. These packages are usually called ``mozilla_voice_stt_cuda``. Files ending in ``.tflite`` are compatible with clients and language bindings built against the `TensorFlow Lite runtime <https://www.tensorflow.org/lite/>`_. These models are optimized for size and performance in low power devices. On desktop platforms, the compatible packages are called ``mozilla_voice_stt_tflite``. On Android and Raspberry Pi, we only publish TensorFlow Lite enabled packages, and they are simply called ``mozilla_voice_stt``. You can see a full list of supported platforms and which TensorFlow runtime is supported at :ref:`supported-platforms-inference`.
44
44
@@ -122,7 +122,7 @@ Alternatively, if you have a supported NVIDIA GPU on Linux, you can install the
122
122
123
123
$ pip3 install mozilla_voice_stt_cuda
124
124
125
-
See the `release notes <https://github.com/mozilla/STT/releases>`_ to find which GPUs are supported. Please ensure you have the required `CUDA dependency <#cuda-dependency>`_.
125
+
See the `release notes <https://github.com/mozilla/DeepSpeech/releases>`_ to find which GPUs are supported. Please ensure you have the required `CUDA dependency <#cuda-dependency>`_.
126
126
127
127
You can update ``mozilla_voice_stt_cuda`` as follows:
128
128
@@ -136,7 +136,7 @@ Note: the following command assumes you `downloaded the pre-trained model <#gett
The ``--scorer`` argument is optional, and represents an external language model to be used when transcribing the audio.
142
142
@@ -165,7 +165,7 @@ Alternatively, if you're using Linux and have a supported NVIDIA GPU, you can in
165
165
166
166
npm install @mozilla-voice/stt-cuda
167
167
168
-
See the `release notes <https://github.com/mozilla/STT/releases>`_ to find which GPUs are supported. Please ensure you have the required `CUDA dependency <#cuda-dependency>`_.
168
+
See the `release notes <https://github.com/mozilla/DeepSpeech/releases>`_ to find which GPUs are supported. Please ensure you have the required `CUDA dependency <#cuda-dependency>`_.
169
169
170
170
See the :ref:`TypeScript client <js-api-example>` for an example of how to use the bindings programatically.
171
171
@@ -194,13 +194,13 @@ also, if you need some binaries different than current master, like ``v0.2.0-alp
194
194
195
195
The script ``taskcluster.py`` will download ``native_client.tar.xz`` (which includes the ``mozilla_voice_stt`` binary and associated libraries) and extract it into the current folder. Also, ``taskcluster.py`` will download binaries for Linux/x86_64 by default, but you can override that behavior with the ``--arch`` parameter. See the help info with ``python util/taskcluster.py -h`` for more details. Specific branches of Mozilla Voice STT or TensorFlow can be specified as well.
196
196
197
-
Alternatively you may manually download the ``native_client.tar.xz`` from the [releases](https://github.com/mozilla/STT/releases).
197
+
Alternatively you may manually download the ``native_client.tar.xz`` from the [releases](https://github.com/mozilla/DeepSpeech/releases).
198
198
199
199
Note: the following command assumes you `downloaded the pre-trained model <#getting-the-pre-trained-model>`_.
A pre-trained English model is available for use and can be downloaded following the instructions in :ref:`the usage docs <usage-docs>`. For the latest release, including pre-trained models and checkpoints, `see the GitHub releases page <https://github.com/mozilla/STT/releases/latest>`_.
33
+
A pre-trained English model is available for use and can be downloaded following the instructions in :ref:`the usage docs <usage-docs>`. For the latest release, including pre-trained models and checkpoints, `see the GitHub releases page <https://github.com/mozilla/DeepSpeech/releases/latest>`_.
34
34
35
-
Quicker inference can be performed using a supported NVIDIA GPU on Linux. See the `release notes <https://github.com/mozilla/STT/releases/latest>`_ to find which GPUs are supported. To run ``mozilla_voice_stt`` on a GPU, install the GPU specific package:
35
+
Quicker inference can be performed using a supported NVIDIA GPU on Linux. See the `release notes <https://github.com/mozilla/DeepSpeech/releases/latest>`_ to find which GPUs are supported. To run ``mozilla_voice_stt`` on a GPU, install the GPU specific package:
36
36
37
37
.. code-block:: bash
38
38
@@ -44,7 +44,7 @@ Quicker inference can be performed using a supported NVIDIA GPU on Linux. See th
Copy file name to clipboardexpand all lines: native_client/dotnet/README.rst
+3-3
Original file line number
Diff line number
Diff line change
@@ -42,11 +42,11 @@ We highly recommend sticking to the recommended versions of CUDA/cuDNN in order
42
42
Getting the code
43
43
----------------
44
44
45
-
We need to clone ``mozilla/STT``.
45
+
We need to clone ``mozilla/DeepSpeech``.
46
46
47
47
.. code-block:: bash
48
48
49
-
git clone https://github.com/mozilla/STT
49
+
git clone https://github.com/mozilla/DeepSpeech
50
50
git submodule sync tensorflow/
51
51
git submodule update --init tensorflow/
52
52
@@ -142,4 +142,4 @@ Be patient, if you enabled AVX/AVX2 and CUDA it will take a long time. Finally y
142
142
Using the generated library
143
143
---------------------------
144
144
145
-
As for now we can only use the generated ``libmozilla_voice_stt.so`` with the C# clients, go to `native_client/dotnet/ <https://github.com/mozilla/STT/tree/master/native_client/dotnet>`_ in your Mozilla Voice STT directory and open the Visual Studio solution, then we need to build in debug or release mode, finally we just need to copy ``libmozilla_voice_stt.so`` to the generated ``x64/Debug`` or ``x64/Release`` directory.
145
+
As for now we can only use the generated ``libmozilla_voice_stt.so`` with the C# clients, go to `native_client/dotnet/ <https://github.com/mozilla/DeepSpeech/tree/master/native_client/dotnet>`_ in your Mozilla Voice STT directory and open the Visual Studio solution, then we need to build in debug or release mode, finally we just need to copy ``libmozilla_voice_stt.so`` to the generated ``x64/Debug`` or ``x64/Release`` directory.
0 commit comments