Speaker Identifier

Find out who the speaker is from the youtube videos. For a detailed explanation of the code, visit the following post. https://mk-minchul.github.io/SpeakerIdentification/

You should install the necessary packages using the requirement.txt

pip install -r /path/to/requirements.txt

If you want to download the youtube video and retrain the model yourself, run the following code.

python main.py

If you want to train with different input vidoes, tweak the moon.txt and son.txt files.

If you want to only run the test using the pretrained model, run the following code.

python test.py

For different input videos for the test, tweak the test.txt file.

This project is licensed under the Apache License - see the LICENSE.md file for details

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
.idea		.idea
models		models
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
batch_helper.py		batch_helper.py
download_youtube.py		download_youtube.py
main.py		main.py
moon.txt		moon.txt
requirements.txt		requirements.txt
son.txt		son.txt
split_on_silence.py		split_on_silence.py
test.py		test.py
test.txt		test.txt

mk-minchul/SpeakerIdentifier