realtime microphone to spectrogram to imagehash

gistfile1.txt

import ffmpeg
import numpy as np
import cv2
import sys

# pip install ffmpeg-python
# pip install opencv-python
# pip install opencv-contrib-python 



process1 = (
    ffmpeg
    .input("default", f='pulse', fragment_size=16, channels=1, rtbufsize="1024B", fflags="nobuffer")
    .filter('showspectrum', s='32x32', mode="combined",slide="scroll",  scale="log")
    .output('pipe:', format='rawvideo', pix_fmt='gray')
    .run_async(pipe_stdout=True)
)


while True:
    in_bytes = process1.stdout.read(32 * 32)
    if not in_bytes:
        break
    in_frame = (
        np
        .frombuffer(in_bytes, np.uint8)
        .reshape([32, 32, 1])
    )
    
    h=cv2.img_hash.pHash(in_frame) # 8-byte hash
    pH=int.from_bytes(h.tobytes(), byteorder='big', signed=False)
    sys.stdout.write(f"got_hash {pH}\n")
    sys.stdout.flush()