download_audio.sh

download_audio.sh

# @Author: richman
# @Date:   2018-03-15
# @Last Modified by:   richman
# @Last Modified time: 2018-03-30

if [[ $# < 1 ]]; then
    echo "Input .csv file .e.g balanced_train_segments.csv"
    exit
fi

inp=$1
njobs=${2:-4}

SAMPLE_RATE=16000

fetch_clip() {

  echo $1
  # echo "Fetching $1 ($2 to $3)..."
  outname="$1_$2_$3"
  if [ -f "${outname}*" ]; then
    # echo "Already have it."
    return
  fi

  youtube-dl https://youtube.com/watch?v=$1 \
      --quiet --extract-audio --audio-format flac --no-warnings --output "$outname.%(ext)s"
    if [ $? -eq 0 ]; then
        downloaded_file=$(find . -name "$outname*")
        ffmpeg -loglevel quiet  -i "$downloaded_file" -ar $SAMPLE_RATE \
        -ss "$2" -to "$3" "./${outname}_out.flac"
        mv "./${outname}_out.flac" "./${outname}.flac"
    fi
}


export SAMPLE_RATE
export -f fetch_clip


grep "^[^#;]" $inp | parallel --resume --joblog job.log --bar -j $njobs --colsep=, fetch_clip {1} {2} {3} > /dev/null