Open mavericky87 opened 2 years ago
because I want to avoid that vosk wastes time recognizing the words that come out of the speakers, and starts again when the answer and therefore the words from the speakers are finished, I have answers in mp3 that start based on what vosk recognizes example: vosk recognizes " what's the weather like today? " the mp3 starts with the answer on the weather, here I want that while the mp3 is in play, vosk goes to pause, and immediately afterwards starts listening again to recognize the words
@nshmyrev excuse the tag if you have a tip for this as soon as you have time, thank you so much for the work you do
Hi. Sorry, I missed this. If you don't want to pass audio to recognizer, just create a variable and if it is false, skip the audio before AcceptWaveform. You can modify variable from other thread. Like here:
https://github.com/alphacep/vosk-api/blob/master/python/example/test_microphone.py#L19
def callback(indata, frames, time, status):
"""This is called (from a separate thread) for each audio block."""
if status:
print(status, file=sys.stderr)
if listening:
q.put(bytes(indata))
then modify listening
on and off
@nshmyrev Hello, I have the same problem, but I did not understand what you wrote. Can you please explain at beginner level?
Can you please explain at beginner level?
I can not. But you can ask questions if you have any
def callback(indata, frames, time, status): """This is called (from a separate thread) for each audio block.""" if status: print(status, file=sys.stderr) if listening: q.put(bytes(indata))
where do we paste the code
Nickolay V. Shmyrev @.***>, 7 May 2024 Sal, 22:31 tarihinde şunu yazdı:
Can you please explain at beginner level?
I can not. But you can ask questions if you have any
— Reply to this email directly, view it on GitHub https://github.com/alphacep/vosk-api/issues/969#issuecomment-2099155049, or unsubscribe https://github.com/notifications/unsubscribe-auth/BIKXBKQBB5V44TE7ZJCIDBLZBET2TAVCNFSM5WOIV2QKU5DIOJSWCZC7NNSXTN2JONZXKZKDN5WW2ZLOOQ5TEMBZHEYTKNJQGQ4Q . You are receiving this because you commented.Message ID: @.***>
In test_microphone.py example
hello I wanted some advice on how to solve a problem, everything works fine, vosk recognizes what I say and then a voice based on what I said, leaves to answer, if I wanted to disable the microphone or otherwise mute so that vosk does it pause while audio comes out of the speakers, and then resumes listening by vosk when the audio from the speakers is finished? All this on Raspberry with python, thank you very much :)