ViDove / evaluation /readme.md
JiaenLiu
Evaluation structure
b0198e8

A newer version of the Gradio SDK is available: 4.37.1

Upgrade

Evaluation:
BLEU (https://github.com/mjpost/sacrebleu)
COMET (https://github.com/Unbabel/COMET)
LLM eval
Eval time stamp

Sep 18 - Sep 25 Proj-t src evaluation

  • scores
  • LLM_eval.py (jiaen)
  • scores.py (wizard)
  • comet
  • sacrebleu
    • alignment.py (david)
    • evaluation.py (not assigned)
  • results
  • mmddyy-HMS-results.csv
  • logs

entry: Python3 evaluation/evaluation.py –pred path/to/pred –gt path/to/gt