This repository is currently being refactored, and therefore files may change.
Sequence-to-sequence model to train speech-to-text systems.
We preprocessed the English translations released by:
and make them available here.
Fisher Spanish speech data is available from LDC (LDC2010S01)
We use Chainer as our deep learning framework
Installation:
- create a conda environment with Python 3:
conda create --name ast python=3
- activate new environment:
source activate ast
- install CuPy
pip install cupy-cuda91
- install chainer
pip install chainer
- check if Chainer detects GPU support. Launch python:
$ python
Python 3.7.1
[GCC 7.3.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import chainer
>>> chainer.backends.cuda.available
True
>>> chainer.backends.cuda.cudnn_enabled
True
>>>
- install NLTK. Used to extract stop word lists for target languages, and for computing evaluation metrics such as BLEU score.
conda install nltk
- install tqdm for progress bar support
conda install tqdm