TensorFlowASR 2.1.0

Almost State-of-the-art Automatic Speech Recognition using Tensorflow 2

TensorFlowASR :zap:

Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2

TensorFlowASR implements some automatic speech recognition architectures such as DeepSpeech2, Jasper, RNN Transducer, ContextNet, Conformer, etc. These models can be converted to TFLite to reduce memory and computation for deployment :smile:

What's New?

Table of Contents

• What's New?
• Table of Contents
• :yum: Supported Models
  • Baselines
  • Publications
• Installation
  • Installing from source (recommended)
  • Installing via PyPi
  • Installing for development
  • Install for Apple Sillicon
  • Running in a container
• Training & Testing Tutorial
• Features Extraction
• Augmentations
• TFLite Convertion
• Pretrained Models
• Corpus Sources
  • English
  • Vietnamese
• How to contribute
• References & Credits
• Contact

:yum: Supported Models

Baselines

• Transducer Models (End2end models using RNNT Loss for training, currently supported Conformer, ContextNet, Streaming Transducer)
• CTCModel (End2end models using CTC Loss for training, currently supported DeepSpeech2, Jasper)

Publications

• Conformer Transducer (Reference: https://arxiv.org/abs/2005.08100) See examples/models/transducer/conformer
• ContextNet (Reference: http://arxiv.org/abs/2005.03191) See examples/models/transducer/contextnet
• RNN Transducer (Reference: https://arxiv.org/abs/1811.06621) See examples/models/transducer/rnnt
• Deep Speech 2 (Reference: https://arxiv.org/abs/1512.02595) See examples/models/ctc/deepspeech2
• Jasper (Reference: https://arxiv.org/abs/1904.03288) See examples/models/ctc/jasper

Installation

For training and testing, you should use git clone for installing necessary packages from other authors (ctc_decoders, rnnt_loss, etc.)

Installing from source (recommended)

git clone https://github.com/TensorSpeech/TensorFlowASR.git
cd TensorFlowASR
# Tensorflow 2.x (with 2.x.x >= 2.5.1)
pip3 install ".[tf2.x]" # or ".[tf2.x-gpu]"

For anaconda3:

conda create -y -n tfasr tensorflow-gpu python=3.8 # tensorflow if using CPU, this makes sure conda install all dependencies for tensorflow
conda activate tfasr
pip install -U tensorflow-gpu # upgrade to latest version of tensorflow
git clone https://github.com/TensorSpeech/TensorFlowASR.git
cd TensorFlowASR
# Tensorflow 2.x (with 2.x.x >= 2.5.1)
pip3 install ".[tf2.x]" # or ".[tf2.x-gpu]"

Installing via PyPi

# Tensorflow 2.x (with 2.x >= 2.3)
pip3 install "TensorFlowASR[tf2.x]" # or pip3 install "TensorFlowASR[tf2.x-gpu]"

Installing for development

git clone https://github.com/TensorSpeech/TensorFlowASR.git
cd TensorFlowASR
pip3 install -e ".[dev]"
pip3 install -e ".[tf2.x]" # or ".[tf2.x-gpu]" or ".[tf2.x-apple]" for apple m1 machine

Install for Apple Sillicon

Due to tensorflow-text is not built for Apple Sillicon, we need to install it with the prebuilt wheel file from sun1638650145/Libraries-and-Extensions-for-TensorFlow-for-Apple-Silicon

git clone https://github.com/TensorSpeech/TensorFlowASR.git
cd TensorFlowASR
pip3 install -e "." # or pip3 install -e ".[dev] for development # or pip3 install "TensorFlowASR[dev]" from PyPi
pip3 install tensorflow~=2.14.0 # change minor version if you want

Do this after installing TensorFlowASR with tensorflow above

TF_VERSION="$(python3 -c 'import tensorflow; print(tensorflow.__version__)')" && \
TF_VERSION_MAJOR="$(echo $TF_VERSION | cut -d'.' -f1,2)" && \
PY_VERSION="$(python3 -c 'import platform; major, minor, patch = platform.python_version_tuple(); print(f"{major}{minor}");')" && \
URL="https://github.com/sun1638650145/Libraries-and-Extensions-for-TensorFlow-for-Apple-Silicon" && \
pip3 install "${URL}/releases/download/v${TF_VERSION_MAJOR}/tensorflow_text-${TF_VERSION_MAJOR}.0-cp${PY_VERSION}-cp${PY_VERSION}-macosx_11_0_arm64.whl"

Running in a container

docker-compose up -d

Training & Testing Tutorial

• For training, please read tutorial_training
• For testing, please read tutorial_testing

FYI: Keras builtin training uses infinite dataset, which avoids the potential last partial batch.

See examples for some predefined ASR models and results

Features Extraction

See features_extraction

Augmentations

See augmentations

TFLite Convertion

After converting to tflite, the tflite model is like a function that transforms directly from an audio signal to text and tokens

See tflite_convertion

Pretrained Models

Go to drive

Corpus Sources

English

Name	Source	Hours
LibriSpeech	LibriSpeech	970h
Common Voice	https://commonvoice.mozilla.org	1932h

Vietnamese

Name	Source	Hours
Vivos	https://ailab.hcmus.edu.vn/vivos	15h
InfoRe Technology 1	InfoRe1 (passwd: BroughtToYouByInfoRe)	25h
InfoRe Technology 2 (used in VLSP2019)	InfoRe2 (passwd: BroughtToYouByInfoRe)	415h

How to contribute

1. Fork the project
2. Install for development
3. Create a branch
4. Make a pull request to this repo

References & Credits

1. NVIDIA OpenSeq2Seq Toolkit
2. https://github.com/noahchalifour/warp-transducer
3. Sequence Transduction with Recurrent Neural Network
4. End-to-End Speech Processing Toolkit in PyTorch
5. https://github.com/iankur/ContextNet

Contact

Huy Le Nguyen

Email: [e-mail]