def test_context():
context = SpeechContext()
# test is_speech
assert not context.is_speech
context.is_speech = True
assert context.is_speech
# test is_active
assert not context.is_active
context.is_active = True
assert context.is_active
# test transcript
assert not context.transcript
context.transcript = "this is a test"
assert context.transcript
# test confidence
assert context.confidence == 0.0
context.confidence = 1.0
assert context.confidence == 1.0
# test reset
context.reset()
assert not context.is_speech
assert not context.is_active
assert not context.transcript
assert context.confidence == 0.0
def _receive(self, context: SpeechContext) -> None:
for response in self._client.streaming_recognize(
self._config, self._drain()):
for result in response.results[:1]:
for alternative in result.alternatives[:1]:
context.transcript = alternative.transcript
context.confidence = alternative.confidence
if context.transcript:
context.event("partial_recognize")
if result.is_final:
if context.transcript:
context.event("recognize")
_LOG.debug("recognize event")
else:
context.event("timeout")
_LOG.debug("timeout event")
def _receive(self, context: SpeechContext) -> None:
self._client.receive()
hypotheses = self._client.response.get("hypotheses")
if hypotheses:
hypothesis = hypotheses[0]
context.transcript = hypothesis["transcript"]
context.confidence = hypothesis["confidence"]
if context.transcript:
context.event("partial_recognize")
if self._client.is_final:
if context.transcript:
context.event("recognize")
_LOG.debug("recognize event")
else:
context.event("timeout")
_LOG.debug("timeout event")
def _detect(self, context: SpeechContext) -> None:
# read the full contents of the encode window and add the batch dimension
# calculate a scalar likelihood that the frame contains a keyword
# with the detect model
frame = self.encode_window.read_all()
frame = np.expand_dims(frame, 0)
posterior = self.detect_model(frame)[0][0]
class_index = np.argmax(posterior)
confidence = posterior[class_index]
if confidence >= self._posterior_threshold:
context.transcript = self.classes[class_index]
context.confidence = confidence
context.event("recognize")
else:
context.event("timeout")
self.reset()
