def update(self, stream: Union[BinaryIO, np.ndarray, bytes]) -> float:
#print('chunk_size:', self.chunk_size)
if isinstance(stream, np.ndarray):
buffer_audio = stream
else:
if isinstance(stream, (bytes, bytearray)):
chunk = stream
else:
chunk = stream.read(self.chunk_size)
if len(chunk) == 0:
raise EOFError
buffer_audio = buffer_to_audio(chunk)
self.window_audio = np.concatenate((self.window_audio, buffer_audio))
if len(self.window_audio) >= self.pr.window_samples:
new_features = vectorize_raw(self.window_audio)
self.window_audio = self.window_audio[len(new_features) *
self.pr.hop_samples:]
if len(new_features) > len(self.mfccs):
new_features = new_features[-len(self.mfccs):]
self.mfccs = np.concatenate(
(self.mfccs[len(new_features):], new_features))
mfccs = self.mfccs
if self.pr.use_delta:
mfccs = add_deltas(self.mfccs)
return self.runner.run(mfccs)
def evaluate(self, audio: np.ndarray) -> np.ndarray:
print('MFCCs...')
mfccs = vectorize_raw(audio)
print('Splitting...')
mfcc_hops = self.args.chunk_size // pr.hop_samples
inputs = np.array([
mfccs[i - pr.n_features:i] for i in range(pr.n_features, len(mfccs), mfcc_hops)
])
print('Predicting...')
predictions = self.runner.predict(inputs)
return predictions