Feature Request : img2audio batch convert.

[wedgeewoo]

Rendering each file in a directory would make it easier for those with potato video cards.

[HIN0209]

Hi, using Jupyter lab, I was successful converting in a batch manner with the code below. All the wav files in the input_dir are converted to 5-second spectrograms.
(reference: https://github.com/thx-pw/riffusion-music2music-colab)

output = "./content/input/spectrogram"
input_dir = "./content/input/wav_clip"

with os.scandir(input_dir) as dirs:
for entry in dirs:
!python file2img.py --input "./content/input/wav_clip/{entry.name}" --output {output} --nmels 512 --maxvol 255 --powerforimage 0.35

[HIN0209]

my prior code needs to be adjusted for indents for the last two lines, obviously.

[lalalune]

Here is a shell script you can run

wavDir=data
imgDir=data_out

for wav in $wavDir/*.wav
do
    img=$imgDir
    python3 file2img.py -i $wav -o $img
done