Jan-19-2021, 10:06 PM
heres a script to detect and record sound that ive been hacking on for a while. it works great, except that its memory usage grows after every successful detection. what am i missing?
#!/usr/bin/env python3 from sys import byteorder from array import array from struct import pack from datetime import datetime import pyaudio import wave import os import time THRESHOLD = 6348 MAX_SILENCE = 500 CHUNK_SIZE = 1024 FORMAT = pyaudio.paInt16 RATE = 44100 MAX_LENGTH = 1024 def is_silent(snd_data): "Returns 'True' if below the 'silent' threshold" return max(snd_data) < THRESHOLD def normalize(snd_data): "Average the volume out" MAXIMUM = 16384 times = float(MAXIMUM)/max(abs(i) for i in snd_data) r = array('h') for i in snd_data: r.append(int(i*times)) return r def trim(snd_data): "Trim the blank spots at the start and end" def _trim(snd_data): snd_started = False r = array('h') for i in snd_data: if not snd_started and abs(i) > THRESHOLD: snd_started = True r.append(i) elif snd_started: r.append(i) return r # Trim to the left snd_data = _trim(snd_data) # Trim to the right snd_data.reverse() snd_data = _trim(snd_data) snd_data.reverse() return snd_data def add_silence(snd_data, seconds): "Add silence to the start and end of 'snd_data' of length 'seconds' (float)" silence = [0] * int(seconds * RATE) r = array('h', silence) r.extend(snd_data) r.extend(silence) return r def record(): """ Record a word or words from the microphone and return the data as an array of signed shorts. Normalizes the audio, trims silence from the start and end, and pads with 0.5 seconds of blank sound to make sure VLC et al can play it without getting chopped off. """ p = pyaudio.PyAudio() stream = p.open(format=FORMAT, channels=1, rate=RATE, input=True, output=True, frames_per_buffer=CHUNK_SIZE) num_silent = 0 num_snd = 0 num_listening = 0 snd_started = False r = array('h') while num_snd < MAX_LENGTH: # little endian, signed short snd_data = array('h', stream.read(CHUNK_SIZE, exception_on_overflow = False)) if byteorder == 'big': snd_data.byteswap() r.extend(snd_data) silent = is_silent(snd_data) if not silent and not snd_started: snd_started = True if snd_started: num_snd += 1 if num_silent > MAX_SILENCE: break if silent: if snd_started: num_silent += 1 if not snd_started: num_listening += 1 if num_listening > 4096: del r[:] num_listening = 0 sample_width = p.get_sample_size(FORMAT) stream.stop_stream() stream.close() p.terminate() del r[0:8000] r = normalize(r) r = trim(r) r = add_silence(r, 0.5) return sample_width, r def record_to_file(path): "Records from the microphone and outputs the resulting data to 'path'" sample_width, data = record() data = pack('<' + ('h'*len(data)), *data) wf = wave.open(path, 'wb') wf.setnchannels(1) wf.setsampwidth(sample_width) wf.setframerate(RATE) wf.writeframes(data) wf.close() if __name__ == '__main__': while True: print("Ready!") recorded = datetime.now() recorded = "testpi1_" + recorded.strftime("%Y-%m-%d--%H-%M-%S") + ".wav" record_to_file("/motion/" + recorded) os.system("./convert-audio.py " + recorded)