Data

Tools

Indexes

Applications

Experiments

Open Source Science

m214a-project

M214A Project Repository for Winter 2024

https://github.com/dotimothy/m214a-project

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

M214A Project Repository for Winter 2024

Basic Info
  • Host: GitHub
  • Owner: dotimothy
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 653 MB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Readme Citation

README.md

M214A-Project

Final Project Repository of M214A for Winter Quarter 2024. Task: Dialect Region Classification of African American Speakers in the CORAAL Dataset

Authors: Keith Chen, Timothy Do, James Shiffer, Thomas Sison

Dependencies

The dependencies with specific versions for this project is listed under requirements.txt.

Setup

  1. Run pip install -r requirements.txt to check and install all Python dependencies.
  2. Download the Project Data W24 ECE M214A Project.zip and unzip as ./W24 ECE M214A Project/
  3. If applying pre-trained data augmentation, the preaugmented training labels and features for the best model are in ./featuresaugmenteddataconst for issues with download time and compatibility. For reference the preaugmented training set can be downloaded from UCLA Box into ./W24 ECE M214A Project/projectdata/ and unzip as augmenteddatawithadjustablechatter in the same folder to extract features and label independently with different hyperparameters, but is not required to test the hidden set.
  4. Run jupyter notebook and open the Project.ipynb to perform the task progressively! For just extracting and testing the best features with the hidden set refer to section 9 of the notebook.

Contact

For issues/questions about the code contact Timothy at timothydo@ucla.edu.

Owner

  • Name: Timothy Do
  • Login: dotimothy
  • Kind: user
  • Location: San Jose, CA

A Bay Area IoT Techie || UCI EECS '23 ⚡

GitHub Events

Total
Last Year

Dependencies

.ipynb_checkpoints/requirements-checkpoint.txt pypi
  • glob2 ==0.7
  • ipython ==8.22.2
  • joblib ==1.3.2
  • librosa ==0.10.1
  • matplotlib ==3.8.3
  • numpy ==1.26.4
  • opensmile ==2.5.0
  • pandas ==2.2.1
  • scikit-learn ==1.4.1.post1
  • scipy ==1.12.0
  • shap ==0.44.1
  • spafe ==0.3.2
  • torchaudio ==2.1.0
  • tqdm ==4.66.2
  • xgboost ==2.0.3