You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

478 B

Routines for DeepSpeech features processing

Several routines for DeepSpeech features processing, like speech features generation for VOCA model.

Installation

pip3 install -r requirements.txt

Usage

Generate wav files:

python3 extract_wav.py --in-video=<you_data_dir>

Generate files with DeepSpeech features:

python3 extract_ds_features.py --input=<you_data_dir>