Lucian Georgescu

Okay, thank you for the answer. I have changed in the following way. In the main() function, besides: ps_set_kws (ps, "kws", "keyword.txt"); ps_set_jsgf_file (ps, "jsgf", "grammar.gram"); I added: ps_set_search (ps, "kws"); ps_set_rawdata_size (ps, 500000); to start by default in kws mode and to set the maximum buffer size (I put a random value, I have no idea how it should be). The recognize_from_microphone() function now looks like this: static void recognize_from_microphone() { ad_rec_t *ad; int16...

Hello, I'm working on a project where I use pockesphinx to recognize commands in real time. This is the commands format (there are some examples): Casandra, turn the lights off. Casandra, turn the lights on. Casandra, change the color of the light. The idea of using a grammar model with garbage loop produces delays (the project runs on Raspberry PI). Reading on the forum topics, I understand that I should use the keyword spotting module to detect when the keyword "Casandra" is spoken and then switch...

Thanks, I will try it. I had a similar idea, to create a pipe between the websocket...

You are right, I create a new InputStream for every received message. If I create...

Hi, I want to create a client-server application for a live transcription task. On...

Hi, I have a few questions about how I could run much faster a DNN recipe. First...

Hi, I want to use the acoustic model trained with Timit database in my own project....

I copied those files and now it works. Thank you!