# ear Audio quality evaluation models

## Setup ``` cd boost conda create -n ear-env python=3.10 conda activate ear-env conda install -c conda-forge ffmpeg=6 pip install -e . pip install -U 'jsonargparse[signatures]>=4.27.7 ``` ## Training ``` CUDA_VISIBLE_DEVICES=1 python main.py fit -c cfg/trainer.yaml -c cfg/model_semantic.yaml -c cfg/data_24khz.yaml CUDA_VISIBLE_DEVICES=2 python main.py fit -c cfg/trainer.yaml -c cfg/model_codec.yaml -c cfg/data_48khz.yaml CUDA_VISIBLE_DEVICES=0 python main.py fit -c cfg/trainer.yaml -c cfg/model_panns.yaml -c cfg/data_48khz.yaml ```