Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bagustris/w2v2-vad

A wrapper for Audeering's wav2vec-based dimensional speech emotion recognition

https://github.com/bagustris/w2v2-vad

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
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.4%) to scientific vocabulary

Keywords

affective-computing sentiment-analysis speech-emotion-recognition
Last synced: 5 months ago · JSON representation

Repository

A wrapper for Audeering's wav2vec-based dimensional speech emotion recognition

Basic Info
  • Host: GitHub
  • Owner: bagustris
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 369 KB
Statistics
  • Stars: 16
  • Watchers: 2
  • Forks: 4
  • Open Issues: 1
  • Releases: 1
Topics
affective-computing sentiment-analysis speech-emotion-recognition
Created almost 4 years ago · Last pushed over 2 years ago
Metadata Files
Readme

README.md

w2v2-vad

A wrapper for Audeering's wav2vector-based dimensional speech emotion recognition (arousal, dominance, and valence).

Input-output

input: any audio file readable by torchaudio at any sample rate (will be resampled to 16000 Hz on the fly)
output: score of valence, arousal, and dominance in a range [0, 1]

Virtual Environment

I recommend using a virtual environment to run this script. You can use either venv or conda. I prefer to use (Mini) conda now over venv. Here is the example.

conda create -n w2v2-vad python=3.8
conda activate w2v2-vad

Installation

pip3 install -r requirements.txt

Usage

python3 predict_vad_w2v2.py input.wav

Arguments

Positional: input file at any sample rate Optional: -s split, `chunks` or `full`, default is full. -d duration, duration in seconds (if the split is chunks, must be specified)

Example

bagus@L140MU:w2v2-vad$ python3 predict_vad_w2v2.py bagus-test_16000.wav Arousal, dominance, and valence #0: [[0.32293236 0.41639617 0.5942142 ]] bagus@L140MU:w2v2-vad$ python3 predict_vad_w2v2.py bagus-test_16000.wav -s chunks -d 2 Arousal, dominance, and valence #0: [[0.3404813 0.42247295 0.35256445]] Arousal, dominance, and valence #1: [[0.22009875 0.322832 0.51018834]] Arousal, dominance, and valence #2: [[0.3478799 0.4332775 0.45645887]] Arousal, dominance, and valence #3: [[0.29967275 0.4038131 0.4949872 ]] Arousal, dominance, and valence #4: [[0.24804251 0.33543587 0.50990975]] Arousal, dominance, and valence #5: [[0.38564402 0.43214017 0.37035757]]

Demo (v1.0)

asciicast

Original repo

https://github.com/audeering/w2v2-how-to

All credit goes to Audeering.

Owner

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

Researcher @aistairc @VibrasticLab

GitHub Events

Total
Last Year

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 36
  • Total Committers: 1
  • Avg Commits per committer: 36.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Bagus Tris Atmaja b****s@y****m 36

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 2.0
  • 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
View more stats
Top Authors
Issue Authors
  • bagustris (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • audeer ==1.17.2
  • audonnx ==0.5.0
  • torchaudio *
.github/workflows/test_predict_w2v2-vad.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite