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 😄

• What's New?
• Table of Contents
• 😋 Supported Models
  • Baselines
  • Publications
• Installation
• Training & Testing Tutorial
• Features Extraction
• Augmentations
• TFLite Convertion
• Pretrained Models
• Corpus Sources
  • English
  • Vietnamese
• How to contribute
• References & Credits
• Contact

• 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)

• Conformer Transducer (Reference: https://arxiv.org/abs/2005.08100) See examples/models/transducer/conformer
• Streaming Conformer (Reference: http://arxiv.org/abs/2010.11395) 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

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

NOTE ONLY FOR APPLE SILICON: TensorFlowASR requires python >= 3.12

See the requirements.[extra].txt files for extra dependencies

git clone https://github.com/TensorSpeech/TensorFlowASR.git
cd TensorFlowASR
./setup.sh [apple|tpu|gpu] [dev]

Running in a container

docker-compose up -d

• 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

See features_extraction

See augmentations

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

See the results on each example folder, e.g. ./examples/models//transducer/conformer/results/sentencepiece/README.md

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

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

Huy Le Nguyen

Email: nlhuy.cs.16@gmail.com