rec_2_detect.py

import time
import pickle
import librosa
import librosa.display
import numpy as np
import pyaudio
import wave
import torch
import subprocess

FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
CHUNK = 1024
RECORD_SECONDS = 6
WAVE_OUTPUT_FILENAME = "file.wav" # path where you want to save your recorded sound file


def spec_to_image(spec, eps=1e-6):
    mean = spec.mean()
    std = spec.std()
    spec_norm = (spec - mean) / (std + eps)
    spec_min, spec_max = spec_norm.min(), spec_norm.max()
    spec_scaled = 255 * (spec_norm - spec_min) / (spec_max - spec_min)
    spec_scaled = spec_scaled.astype(np.uint8)
    return spec_scaled

def get_melspectrogram_db(file_path, sr=None, n_fft=2048, hop_length=512, n_mels=128, fmin=20, fmax=8300, top_db=80):
  wav,sr = librosa.load(file_path,sr=sr)
  if wav.shape[0]<5*sr:
    wav=np.pad(wav,int(np.ceil((5*sr-wav.shape[0])/2)),mode='reflect')
  else:
    wav=wav[:5*sr]
  spec=librosa.feature.melspectrogram(y=wav, sr=sr, n_fft=n_fft,
              hop_length=hop_length,n_mels=n_mels,fmin=fmin,fmax=fmax)
  spec_db=librosa.power_to_db(spec,top_db=top_db)
  return spec_db

t1 = time.time()

audio = pyaudio.PyAudio()

# start Recording
stream = audio.open(format=FORMAT, channels=CHANNELS,
                rate=RATE, input=True,
                frames_per_buffer=CHUNK)
print("recording...")
stream.start_stream()
frames = []
 
# for recording 
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    frames.append(data)
print("finished recording")
 
# stop Recording
stream.stop_stream()

while stream.is_active():
    time.sleep(0.25)

stream.close()
audio.terminate()

waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
waveFile.setnchannels(CHANNELS)
waveFile.setsampwidth(audio.get_sample_size(FORMAT))
waveFile.setframerate(RATE)
waveFile.writeframes(b''.join(frames))
waveFile.close()


device=torch.device('cuda:0')



with open('indtocat.pkl','rb') as f: # specify path to pickle file
  indtocat = pickle.load(f)

resnet_model = torch.load("esc50resnet.pth") # specify path to saved pytorch model file



filename='file.wav' # path to retrieve previously recorded and saved sound file 
spec=spec_to_image(get_melspectrogram_db(filename))
spec_t=torch.tensor(spec).to(device, dtype=torch.float32)
pr=resnet_model.forward(spec_t.reshape(1,1,*spec_t.shape))
ind = pr.argmax(dim=1).cpu().detach().numpy().ravel()[0]
t2=time.time()
print("{} seconds".format(t2-t1))
print(indtocat[ind])
if indtocat[ind] == 'coughing':
  PREDICT = 'python predict.py file.wav'
  subprocess.run(PREDICT, shell=True)