Optimized for python 3.6
This project serves as a transcriber for short - seconds length - and long audios - up 10 minutes audios and down 30 minutes audio. It uses some services from Google Cloud.
For installing the requirements, in your venv or anaconda env, just run the following command:
pip install -r requirements.txt
.
└── evil-eye
├── data
│ ├── sample_audio_1.mp3
│ ├── ...
│ └── sample_audio_2.mp3
├── docs
│ └── CREDITS
├── src
│ ├── __init__.py
│ ├── settings.json
│ └── speech.py
├── tests
│ └── unittests
│ └── __init__.py
├── .gitignore
├── LICENSE
├── README.md
└── requirements.txt
- data: The data dir. Group of non-script support files.
- docs: The documentation dir.
- src: The scripts & source code dir.
- tests: The unittests dir.
Section aimed on clarifying some running issues.
For running it, at the ~/src
directory just run:
python speech.py
or, if importing it as a module, just run:
from speech import local_short_recognition, cloud_long_recognize
if __name__ == '__main__':
local_short_recognition('path/to/file')
cloud_long_recognize('gs://[bucket]/[file]')
{
"type": "",
"project_id": "",
"private_key_id": "",
"private_key": "",
"client_email": "",
"client_id": "",
"auth_uri": "",
"token_uri": "",
"auth_provider_x509_cert_url": "",
"client_x509_cert_url": ""
}