def decodeStream(self, session: DialogSession) -> Optional[ASRResult]:
super().decodeStream(session)
recorder = Recorder(self._timeout, session.user, session.siteId)
self.ASRManager.addRecorder(session.siteId, recorder)
self._recorder = recorder
with Stopwatch() as processingTime:
with recorder as stream:
audioStream = stream.audioStream()
# noinspection PyUnresolvedReferences
try:
requests = (types.StreamingRecognizeRequest(
audio_content=content) for content in audioStream)
responses = self._client.streaming_recognize(
self._streamingConfig, requests)
result = self._checkResponses(session, responses)
except:
self.logWarning('Failed ASR request')
self.end()
return ASRResult(
text=result[0],
session=session,
likelihood=result[1],
processingTime=processingTime.time) if result else None
def decodeStream(self, session: DialogSession) -> Optional[ASRResult]:
super().decodeStream(session)
result = None
with Stopwatch() as processingTime:
with Recorder(self._timeout) as recorder:
self.ASRManager.addRecorder(session.siteId, recorder)
self._recorder = recorder
streamContext = self._model.createStream()
for chunk in recorder:
if not chunk:
break
self._model.feedAudioContent(
streamContext, np.frombuffer(chunk, np.int16))
result = self._model.intermediateDecode(streamContext)
self.partialTextCaptured(session=session,
text=result,
likelihood=1,
seconds=0)
text = self._model.finishStream(streamContext)
self.end(session)
return ASRResult(
text=text,
session=session,
likelihood=1.0,
processingTime=processingTime.time) if result else None
def decodeStream(self, session: DialogSession) -> Optional[ASRResult]: super().decodeStream(session) result = None with Stopwatch() as processingTime: with Recorder(self._timeout) as recorder: self.ASRManager.addRecorder(session.siteId, recorder) self._decoder.start_utt() inSpeech = False for chunk in recorder: if self._timeout.isSet(): break self._decoder.process_raw(chunk, False, False) if self._decoder.get_in_speech() != inSpeech: inSpeech = self._decoder.get_in_speech() if not inSpeech: self._decoder.end_utt() result = self._decoder.hyp() if self._decoder.hyp() else None break self.end(recorder, session) return ASRResult( text=result.hypstr.strip(), session=session, likelihood=self._decoder.hyp().prob, processingTime=processingTime.time ) if result else None
def decodeStream(self, session: DialogSession) -> Optional[ASRResult]:
super().decodeStream(session)
result = None
previous = ''
with Stopwatch() as processingTime:
with Recorder(self._timeout, session.user,
session.deviceUid) as recorder:
self.ASRManager.addRecorder(session.deviceUid, recorder)
self._recorder = recorder
streamContext = self._model.createStream()
for chunk in recorder:
if not chunk:
break
streamContext.feedAudioContent(
np.frombuffer(chunk, np.int16))
result = streamContext.intermediateDecode()
if result and result != previous:
previous = result
self.partialTextCaptured(session=session,
text=result,
likelihood=1,
seconds=0)
text = streamContext.finishStream()
self._triggerFlag.clear()
self.end()
return ASRResult(
text=text,
session=session,
likelihood=1.0,
processingTime=processingTime.time) if result else None
def decodeStream(self, session: DialogSession) -> Optional[ASRResult]:
super().decodeStream(session)
recorder = Recorder(self._timeout)
self.ASRManager.addRecorder(session.siteId, recorder)
with recorder as stream:
audioStream = stream.audioStream()
requests = (types.StreamingRecognizeRequest(audio_content=content)
for content in audioStream)
responses = self._client.streaming_recognize(
self._streamingConfig, requests)
result = self._checkResponses(session, responses)
self.end(recorder, session)
return ASRResult(text=result[0],
session=session,
likelihood=result[1],
processingTime=10) if result else None
def decodeStream(self, session: DialogSession) -> Optional[ASRResult]:
super().decodeStream(session)
result = None
counter = 0
with Stopwatch() as processingTime:
with Recorder(self._timeout, session.user,
session.deviceUid) as recorder:
self.ASRManager.addRecorder(session.deviceUid, recorder)
self._recorder = recorder
self._decoder.start_utt()
inSpeech = False
for chunk in recorder:
if self._timeout.isSet():
break
self._decoder.process_raw(chunk, False, False)
hypothesis = self._decoder.hyp()
if hypothesis:
counter += 1
if counter == 10:
self.partialTextCaptured(session,
hypothesis.hypstr,
hypothesis.prob,
processingTime.time)
counter = 0
if self._decoder.get_in_speech() != inSpeech:
inSpeech = self._decoder.get_in_speech()
if not inSpeech:
self._decoder.end_utt()
result = self._decoder.hyp() if self._decoder.hyp(
) else None
break
self.end()
return ASRResult(
text=result.hypstr.strip(),
session=session,
likelihood=self._decoder.hyp().prob,
processingTime=processingTime.time) if result else None
