Speech is an open-source package to build end-to-end models for automatic
speech recognition. Sequence-to-sequence models with attention,
Connectionist Temporal Classification and the RNN Sequence Transducer
are currently supported.
The goal of this software is to facilitate research in end-to-end models for
speech recognition. The models are implemented in PyTorch.
The software has only been tested in Python3.6.
We will not be providing backward compatability for Python2.7.
Install
We recommend creating a virtual environment and installing the python
requirements there.
To see the available options for each script use -h:
python {train, eval}.py -h
Examples
For examples of model configurations and datasets, visit the examples
directory. Each example dataset should have instructions and/or scripts for
downloading and preparing the data. There should also be one or more model
configurations available. The results for each configuration will documented in
each examples corresponding README.md.