class PocketSphinxWUW(WUWInterface):
def __init__(self, keyword: str, kws_threshold: float):
self._decoder = Pocketsphinx(keyphrase=keyword,
lm=False,
kws_threshold=kws_threshold)
self._sound = pyaudio.PyAudio()
self._audio_stream = self._sound.open(rate=_SAMPLE_RATE,
channels=1,
format=pyaudio.paInt16,
input=True,
frames_per_buffer=_FRAME_LENGTH)
def prepare(self) -> None:
print("starting utterance")
self._audio_stream.start_stream()
self._decoder.start_utt()
print("started utterance")
def process(self) -> bool:
buf = self._audio_stream.read(_FRAME_LENGTH)
if buf:
self._decoder.process_raw(buf, False, False)
else:
return False
if self._decoder.hyp():
print(self._decoder.hyp().hypstr)
# print([(seg.word, seg.prob, seg.start_frame, seg.end_frame) for seg in self._decoder.seg()])
# print("Detected keyphrase, restarting search")
# for best, i in zip(self._decoder.nbest(), range(10)):
# print(best.hypstr, best.score)
print("ending utterance")
self._decoder.end_utt()
self._audio_stream.stop_stream()
print("ended utterance")
return True
return False
def terminate(self) -> None:
if self._audio_stream is not None:
self._audio_stream.close()
if self._sound is not None:
self._sound.terminate()
p = pyaudio.PyAudio() # Create an interface to PortAudio
# See PyAudio Documentation
stream = p.open(format=sample_format,
channels=channels,
rate=fs,
frames_per_buffer=chunk,
input=True)
print("Running as a daemon")
print("Recording")
#this is the only one that needs PyAudio it seems
while True:
ps.start_utt()
# When there is silence, assume they stopped speaking
while stream.get_read_available() > 0:
data = stream.read(chunk)
ps.process_raw(data, False, False)
frames.append(data)
ps.end_utt() # This is not part of the While loop
# This prevents it from printing silence
if (ps.hypothesis() != ''):
print(ps.hypothesis())
frames = []
stream.stop_stream()
stream.close()
p.terminate()
