https://github.com/cuc-zihang-liu/audioevaluation

多种音频评估方法复现

https://github.com/cuc-zihang-liu/audioevaluation

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 (4.3%) to scientific vocabulary

Keywords

audio clap clip evaluation lpips rewas
Last synced: 5 months ago · JSON representation

Repository

多种音频评估方法复现

Basic Info
  • Host: GitHub
  • Owner: CUC-ZIHANG-LIU
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 135 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
audio clap clip evaluation lpips rewas
Created 10 months ago · Last pushed 8 months ago
Metadata Files
Readme

README.md

  • AudioLDM:
  • CLAPScore: CLAP (Contrastive Language-Audio Pretraining)
  • CLIPScore: CLIP (Contrastive Language-Image Pretraining)
  • Frchet Audio Distance (FAD): VGGish
  • LPIPS (Learned Perceptual Image Patch Similarity):
  • ReWaS (Read, Watch and Scream!): (Energy MAE)CLAP Score(AV-align Score)

. AudioLDM-training-finetuning-main/ # AudioLDM CLAPScore_for_LASS-main/ # CLAPScore CLIPScore-main/ # CLIPScore FAD_fadtk-main/ # Frchet Audio Distance (FAD) LPIPS/ # LPIPS ReWaS/ # ReWaS README.md #

Python

requirements.txt pyproject.toml

** 1 pip ( CLIPScore-main )** bash cd CLIPScore-main/ python -m venv venv source venv/bin/activate # on Windows use `venv\Scripts\activate` pip install -r requirements.txt

** 2 poetry ( FAD_fadtk-main )** bash cd FAD_fadtk-main/ pip install poetry poetry install

README.md

AudioLDM

AudioLDM - *: bash_train.sh - *: bash_eval.sh - ****: audioldm_train/infer.py

CLAPScore

  • ****: CLAPScore_for_LASS-main/main.py

CLIPScore

  • ****: CLIPScore-main/clipscore.py
  • ****: example/ flickr8k_example/

Frchet Audio Distance (FAD)

FAD_fadtk-main fadtk

- ****: python -m fadtk --gt-path /path/to/real_audio --test-path /path/to/generated_audio

LPIPS

LPIPS - *: lpips_2imgs.py - *: lpips_2dirs.py

ReWaS

  • ****: test.py
  • ****: evaluation/
    • eval_MAE.py:
    • clap_score.py: CLAP
    • av_align_score.py:

Owner

  • Name: 刘子航
  • Login: CUC-ZIHANG-LIU
  • Kind: user
  • Company: 中国传媒大学

GitHub Events

Total
  • Watch event: 1
  • Push event: 1
Last Year
  • Watch event: 1
  • Push event: 1