Speaker diarization on VoxData — benchmarked state-of-the-art speaker embedding models against each other, built a custom diarization model, and compared clustering strategies.
4
stars
81
commits
Jupyter Notebook
primary language
Jun 28, 2024
updated
This code was used to perform Speaker diarization from the Voxdata dataset. The project wished to compare different state of the art models against each other and their embedings. Lastly the project attempted to build a custom model to perform speaker diarization and do different clustering methods to compare the results. Most of the code can be seen in the Main code section. The code was written in Python. We received the grade A
76 commits
5 commits
Jupyter Notebook
95.4%
Python
4.6%
Speaker diarization on VoxData — benchmarked state-of-the-art speaker embedding models against each other, built a custom diarization model, and compared clustering strategies.
4
stars
81
commits
Jupyter Notebook
primary language
Jun 28, 2024
updated
This code was used to perform Speaker diarization from the Voxdata dataset. The project wished to compare different state of the art models against each other and their embedings. Lastly the project attempted to build a custom model to perform speaker diarization and do different clustering methods to compare the results. Most of the code can be seen in the Main code section. The code was written in Python. We received the grade A
76 commits
5 commits
Jupyter Notebook
95.4%
Python
4.6%