experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Bump VERSION to 0.9.2

Browse Source
This commit is contained in:
Reuben Morais 2020-12-03 18:35:16 +02:00
parent cf2d7e636a
commit b2920c7557
5 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
doc/TRAINING.rst
View File

@ -15,11 +15,11 @@ Prerequisites for training a model
Getting the training code Getting the training code
^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^
Clone the latest released stable branch from Github (e.g. 0.9.1, check `here <https://github.com/mozilla/DeepSpeech/releases>`_): Clone the latest released stable branch from Github (e.g. 0.9.2, check `here <https://github.com/mozilla/DeepSpeech/releases>`_):
.. code-block:: bash .. code-block:: bash
git clone --branch v0.9.1 https://github.com/mozilla/DeepSpeech git clone --branch v0.9.2 https://github.com/mozilla/DeepSpeech
If you plan on committing code or you want to report bugs, please use the master branch. If you plan on committing code or you want to report bugs, please use the master branch.

8
doc/USING.rst
View File

@ -37,8 +37,8 @@ If you want to use the pre-trained English model for performing speech-to-text,
.. code-block:: bash .. code-block:: bash
wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.1/deepspeech-0.9.1-models.pbmm wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.2/deepspeech-0.9.2-models.pbmm
wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.1/deepspeech-0.9.1-models.scorer wget https://github.com/mozilla/DeepSpeech/releases/download/v0.9.2/deepspeech-0.9.2-models.scorer
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 ``deepspeech``. These files are also compatible with CUDA enabled clients and language bindings. These packages are usually called ``deepspeech-gpu``. 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 ``deepspeech-tflite``. On Android and Raspberry Pi, we only publish TensorFlow Lite enabled packages, and they are simply called ``deepspeech``. You can see a full list of supported platforms and which TensorFlow runtime is supported at :ref:`supported-platforms-inference`. 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 ``deepspeech``. These files are also compatible with CUDA enabled clients and language bindings. These packages are usually called ``deepspeech-gpu``. 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 ``deepspeech-tflite``. On Android and Raspberry Pi, we only publish TensorFlow Lite enabled packages, and they are simply called ``deepspeech``. You can see a full list of supported platforms and which TensorFlow runtime is supported at :ref:`supported-platforms-inference`.
@ -136,7 +136,7 @@ Note: the following command assumes you `downloaded the pre-trained model <#gett
.. code-block:: bash .. code-block:: bash
deepspeech --model deepspeech-0.9.1-models.pbmm --scorer deepspeech-0.9.1-models.scorer --audio my_audio_file.wav deepspeech --model deepspeech-0.9.2-models.pbmm --scorer deepspeech-0.9.2-models.scorer --audio my_audio_file.wav
The ``--scorer`` argument is optional, and represents an external language model to be used when transcribing the audio. The ``--scorer`` argument is optional, and represents an external language model to be used when transcribing the audio.
@ -200,7 +200,7 @@ Note: the following command assumes you `downloaded the pre-trained model <#gett
.. code-block:: bash .. code-block:: bash
./deepspeech --model deepspeech-0.9.1-models.pbmm --scorer deepspeech-0.9.1-models.scorer --audio audio_input.wav ./deepspeech --model deepspeech-0.9.2-models.pbmm --scorer deepspeech-0.9.2-models.scorer --audio audio_input.wav
See the help output with ``./deepspeech -h`` for more details. See the help output with ``./deepspeech -h`` for more details.

12
doc/index.rst
View File

@ -20,15 +20,15 @@ To install and use DeepSpeech all you have to do is:
pip3 install deepspeech pip3 install deepspeech
# Download pre-trained English model files # Download pre-trained English model files
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.1/deepspeech-0.9.1-models.pbmm curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.2/deepspeech-0.9.2-models.pbmm
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.1/deepspeech-0.9.1-models.scorer curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.2/deepspeech-0.9.2-models.scorer
# Download example audio files # Download example audio files
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.1/audio-0.9.1.tar.gz curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.9.2/audio-0.9.2.tar.gz
tar xvf audio-0.9.1.tar.gz tar xvf audio-0.9.2.tar.gz
# Transcribe an audio file # Transcribe an audio file
deepspeech --model deepspeech-0.9.1-models.pbmm --scorer deepspeech-0.9.1-models.scorer --audio audio/2830-3980-0043.wav deepspeech --model deepspeech-0.9.2-models.pbmm --scorer deepspeech-0.9.2-models.scorer --audio audio/2830-3980-0043.wav
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>`_. 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>`_.
@ -44,7 +44,7 @@ Quicker inference can be performed using a supported NVIDIA GPU on Linux. See th
pip3 install deepspeech-gpu pip3 install deepspeech-gpu
# Transcribe an audio file. # Transcribe an audio file.
deepspeech --model deepspeech-0.9.1-models.pbmm --scorer deepspeech-0.9.1-models.scorer --audio audio/2830-3980-0043.wav deepspeech --model deepspeech-0.9.2-models.pbmm --scorer deepspeech-0.9.2-models.scorer --audio audio/2830-3980-0043.wav
Please ensure you have the required :ref:`CUDA dependencies <cuda-inference-deps>`. Please ensure you have the required :ref:`CUDA dependencies <cuda-inference-deps>`.

4
native_client/swift/deepspeech_ios_test/SpeechRecognitionImpl.swift
View File

@ -26,8 +26,8 @@ class SpeechRecognitionImpl : NSObject, AVCaptureAudioDataOutputSampleBufferDele
private var audioData = Data() private var audioData = Data()
override init() { override init() {
let modelPath = Bundle.main.path(forResource: "deepspeech-0.9.1-models", ofType: "tflite")! let modelPath = Bundle.main.path(forResource: "deepspeech-0.9.2-models", ofType: "tflite")!
let scorerPath = Bundle.main.path(forResource: "deepspeech-0.9.1-models", ofType: "scorer")! let scorerPath = Bundle.main.path(forResource: "deepspeech-0.9.2-models", ofType: "scorer")!
model = try! DeepSpeechModel(modelPath: modelPath) model = try! DeepSpeechModel(modelPath: modelPath)
try! model.enableExternalScorer(scorerPath: scorerPath) try! model.enableExternalScorer(scorerPath: scorerPath)

2
training/deepspeech_training/VERSION
View File

@ -1 +1 @@
0.9.1 0.9.2