Speaker identification system can automatically identify the person speaking in an audio file given a group of predefined speakers. For testing, an unseen audio is compared against the provided group of speakers, and in the case there is a match found. The speaker's identity is returned.
You can download our project report from here
- Create a new environment with python 3.6 version because python 3.7 or higher does not support pyaudio package.
conda create -n test python=3.6
conda activate test
- Clone this project:
git clone https://github.com/hhoanguet/speaker-identification.git
cd speaker-identification
- Install all dependencies in requirements.txt, it may take a few minutes.
pip install -r requirements.txt
- Our speaker identification app is ready to run:
streamlit run app.py
Hoang Huy Nguyen
Github: hhoanguet
Hoang Xuan Nguyen
Github: hoangngx