Project DeepSpeech

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.

NOTE: This documentation applies to the master branch of DeepSpeech only. If you're using a stable release, you must use the documentation for the corresponding version by using GitHub's branch switcher button above.

To install and use deepspeech all you have to do is:

# Create and activate a virtualenv
virtualenv -p python3 $HOME/tmp/deepspeech-venv/
source $HOME/tmp/deepspeech-venv/bin/activate

# Install DeepSpeech
pip3 install deepspeech

# Download pre-trained English model and extract
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.6.0/deepspeech-0.6.0-models.tar.gz
tar xvf deepspeech-0.6.0-models.tar.gz

# Download example audio files
curl -LO https://github.com/mozilla/DeepSpeech/releases/download/v0.6.0/audio-0.6.0.tar.gz
tar xvf audio-0.6.0.tar.gz

# Transcribe an audio file
deepspeech --model deepspeech-0.6.0-models/output_graph.pbmm --lm deepspeech-0.6.0-models/lm.binary --trie deepspeech-0.6.0-models/trie --audio audio/2830-3980-0043.wav

A pre-trained English model is available for use and can be downloaded using the instructions below. Currently, only 16-bit, 16 kHz, mono-channel WAVE audio files are supported in the Python client. A package with some example audio files is available for download in our release notes.

Quicker inference can be performed using a supported NVIDIA GPU on Linux. See the release notes to find which GPUs are supported. To run deepspeech on a GPU, install the GPU specific package:

# Create and activate a virtualenv
virtualenv -p python3 $HOME/tmp/deepspeech-gpu-venv/
source $HOME/tmp/deepspeech-gpu-venv/bin/activate

# Install DeepSpeech CUDA enabled package
pip3 install deepspeech-gpu

# Transcribe an audio file.
deepspeech --model deepspeech-0.6.0-models/output_graph.pbmm --lm deepspeech-0.6.0-models/lm.binary --trie deepspeech-0.6.0-models/trie --audio audio/2830-3980-0043.wav

Please ensure you have the required CUDA dependencies.

See the output of deepspeech -h for more information on the use of deepspeech. (If you experience problems running deepspeech, please check required runtime dependencies).

Table of Contents

• Using a Pre-trained Model
  • CUDA dependency
  • Getting the pre-trained model
  • Model compatibility
  • Using the Python package
  • Using the Node.JS package
  • Using the Command Line client
  • Installing bindings from source
  • Third party bindings
• Trying out DeepSpeech with examples
  • Microphone VAD streaming
  • FFMPEG VAD streaming
  • .NET framework
  • Node.JS wav
  • VAD transcriber
• Training your own Model
  • Prerequisites for training a model
  • Getting the training code
  • Installing Python dependencies
  • Recommendations
  • Common Voice training data
  • Training a model
  • Checkpointing
  • Exporting a model for inference
  • Exporting a model for TFLite
  • Making a mmap-able model for inference
  • Continuing training from a release model
  • Training with Augmentation
• Contribution guidelines
• Contact/Getting Help