https://github.com/bagustris/compare2023

For ComParE 2023 Challenge

https://github.com/bagustris/compare2023

Science Score: 36.0%

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
  • Committers with academic emails
    1 of 4 committers (25.0%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

For ComParE 2023 Challenge

Basic Info
  • Host: GitHub
  • Owner: bagustris
  • Language: Python
  • Default Branch: master
  • Size: 2.22 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 3 years ago · Last pushed about 3 years ago
Metadata Files
Readme

README.md

Forked from EIHW/ComParE2023

ComParE23 - The Hume-Prosody Corpus (HP-C)

This repository provides the code for running my participation for The Hume-Prosody Corpus (HP-C) subchallenge of ComParE2023 (excluding feature extraction).

Getting the code

Clone this repository and checkout the correct branch: bash git clone https://github.com/bagustris/ComParE2023

Adding the data

Drop the data into ./data (~40GB), creating this directory structure: console data ├── features │ ├── audeep │ ├── deepspectrum │ ├── opensmile │ └── wav2vec ├── lab ├── raw │ └── wav └── wav You can make a soft link (like in this repo) if your data is located elsewhere (e.g., in /data/).

ln -sf /data/14_ComParE23_HPC_AIST-SPRT/data ./data

Creating Virtual Environments via Miniconda

Create a virtual environment with Python 3.9:

conda create -n ComParE2023 python=3.9

Install dependencies:
pip install -r requirements.txt

Run the experiments:
python3 src/ml/svm.py wav2vec

Calculate the results' score:
python3 src/ml/metrics.py wav2vec

Extracting features

To extract features from Hugging Face, you can use feat_extract.py with arguments name [output directory] and Hugging Face model name [e.g. facebook/wav2vec2-large-xlsr-53].

Format:
./feat_extract.py [output directory] [Hugging Face model name] [device]

Example: bash ./feat_extract.py xlsr-53 jonatasgrosman/wav2vec2-large-xlsr-53-english

You need to change permission (chmod +x feat_extract.py) to run the script directly.

Owner

  • Name: Bagus Tris Atmaja
  • Login: bagustris
  • Kind: user
  • Location: Tsukuba
  • Company: AIST

Researcher @aistairc @VibrasticLab

GitHub Events

Total
Last Year

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 26
  • Total Committers: 4
  • Avg Commits per committer: 6.5
  • Development Distribution Score (DDS): 0.462
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
B Atmaja b****a@a****p 14
aliceebaird a****d@g****m 5
Maurice Gerczuk m****k@i****e 4
aliceebaird a****e@h****i 3
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels