tpulkit / txt2vid

Other
99 stars 18 forks source link

What could i do if i`d like to use local packages of TTS and SST? #8

Closed ZJ-CAI closed 2 years ago

ZJ-CAI commented 2 years ago

Could you pls tell me which python file should be modified. Thanks

shubhamchandak94 commented 2 years ago

Hi, thanks for your interest in this!

For TTS, the main code is inference_streaming_pipeline.py where it sets the parameters and launches the threads for the Google or Resemble TTS. As you can see there the Resemble part requires multiple threads because it uses a callback mechanism to receive the audio. So in your case the google TTS path might be more straightforward to emulate. The actual thread handler functions which do the TTS calls are in thread_handlers.py. The function names are self-explanatory, you can focus on text_input_google_thread_handler.

STT is run on the sender end, so it's in a different part of the codebase. The file is input_stream_socket.py and you will want to focus on the code that runs when text_input_from == 'Google'.

Let us know if you have further questions, we'll be happy to help.

Shubham

ZJ-CAI commented 2 years ago

Thank you for your detailed explanation. It really helps a lot, thank you once more!