olegchomp
olegchomp
Hi! Will be great to have option to send/recieve both PNG/JPEG. It might be some checkbox to switch parameter.
Does this package support Negative prompts? So if yes, how to use in txt file?
Hi! Try to download model and have this error: 
Thank you for great repo! I'm interesting in way to use it with live feed, for ex. cv2 webcam.
Thanks for great repo again ) It will be great to have something like on_sentence_START_synthesized, so sentence can be printed before the speech started.
Hi! I found ```recorder.abort()``` function, and think it will be great to have something: 1) Always listen for wake word in background, even if transcripting. 2) If wake word detected...
Hi! Is there any easy way to switch wakeword detection from porcupine to whisper?
Difference is around 5 FPS, tested with sd_turbo & 1 batch size. On inspect trt engine found that faster engine have different info inside. Also there is difference size slower...