SevaSk / ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.
https://github.com/SevaSk/ecoute
MIT License
5.89k stars 827 forks source link

Ecoute is transcribing the speaker and my speech on the left hand screen in the GUI, but no output on the right hand screen. #69

Closed ragar01 closed 1 year ago

ragar01 commented 1 year ago

Ecoute is transcribing Speaker and my speech into words on the GUI, but no output on the right hand column.

The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details. def backtrace(trace: np.ndarray): [INFO] Adjusting for ambient noise from Default Mic. Please make some noise from the Default Mic... [INFO] Completed ambient noise adjustment for Default Mic. [INFO] Adjusting for ambient noise from Default Speaker. Please make or play some noise from the Default Speaker... [INFO] Completed ambient noise adjustment for Default Speaker. [INFO] Whisper using GPU: False READY

SevaSk commented 1 year ago

If there was an issue with the GPT reponse it should show that in console.

Could you also try using

python main.py --api
ragar01 commented 1 year ago

PS C:\WINDOWS\system32\ecoute> python main.py --api C:\Users\Timeout-2\AppData\Local\Programs\Python\Python310\lib\site-packages\whisper\timing.py:58: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details. def backtrace(trace: np.ndarray): [INFO] Adjusting for ambient noise from Default Mic. Please make some noise from the Default Mic... [INFO] Completed ambient noise adjustment for Default Mic. [INFO] Adjusting for ambient noise from Default Speaker. Please make or play some noise from the Default Speaker... [INFO] Completed ambient noise adjustment for Default Speaker. READY

ragar01 commented 1 year ago

Does not transcribe anything and no output from GPT is seen.

Nimishbansal-16 commented 1 year ago

in my case its also showing no output, because in the terminal its saying that I have exceeded my current quota. Can you guys explain how many api calls get made on using this, at what interval call is made, and which plan do i need to use, because from starting its showing quota exceeded however i havent used it once

SevaSk commented 1 year ago

Hey! To use ChatGPT with your open ai key you need to set up billing on ur open ai account https://stackoverflow.com/questions/75898276/openai-chatgpt-gpt-3-5-api-error-429-you-exceeded-your-current-quota-please