def process_wav_file(stream):
audio_embedder = vggish_embeddings.VGGishEmbedder(None)
processed_embedding = audio_embedder.convert_audio_to_embedding(stream)
p = predict_laugh(np.expand_dims(processed_embedding, axis=0))
print('Laugh Score: {}'.format(p))
return p
@eel.expose
def saveEel(param):
print("Saving file...")
# writer.close()
# writer = open("l_" + str(datetime.now()), 'w')
writer.write("NEW SESSION\n")
print("New file started")
return
eel.start('index.html', block=False)
if __name__ == '__main__':
model = keras.models.load_model(FLAGS.keras_model)
audio_embed = vggish_embeddings.VGGishEmbedder()
context = zmq.Context()
socket = context.socket(zmq.REP)
socket.bind("tcp://*:5555")
writer = open("l_" + str(datetime.now()) + ".csv", 'w')
window = [0.5] * FLAGS.avg_window
with MicrophoneStream(RATE, CHUNK) as stream:
audio_generator = stream.generator()
# vol = np
for chunk in audio_generator:
try:
arr = np.frombuffer(chunk, dtype=np.int16)
vol = np.sqrt(np.mean(arr**2))
MODEL_PATH = '/Users/kaushikandra/laughter-detection/LaughDetection/Models/LSTM_SingleLayer_100Epochs.h5'
def predict_laugh(processed_embedding):
model = keras.models.load_model(MODEL_PATH)
return model.predict(processed_embedding)
def process_wav_file(stream):
audio_embedder = vggish_embeddings.VGGishEmbedder(None)
processed_embedding = audio_embedder.convert_audio_to_embedding(stream)
p = predict_laugh(np.expand_dims(processed_embedding, axis=0))
print('Laugh Score: {}'.format(p))
return p
if __name__ == '__main__':
audio_embedder = vggish_embeddings.VGGishEmbedder(FLAGS.tfrecord_file)
if FLAGS.wav_directory:
files = glob.glob(FLAGS.wav_directory+'/*.wav')
embeddings = [audio_embedder.convert_audio_to_embedding(f) for f in files]
max_len = np.max([e.shape[0] for e in embeddings])
embeddings = np.array([np.append(e, np.zeros([(max_len - e.shape[0]), 128], np.float32), axis=0) for e in embeddings])
scores = predict_laugh(embeddings)
for name, score in zip(files, scores[:, 0]):
print('{:>12}: {:0.6f}'.format(name, score))
else:
processed_embedding = audio_embedder.convert_audio_to_embedding(FLAGS.wav_file)
p = predict_laugh(np.expand_dims(processed_embedding, axis=0))
print('Laugh Score: {}'.format(p))