ExternalVendorCode/ecoute

mirror of https://github.com/SevaSk/ecoute.git synced 2025-02-23 10:00:19 +00:00

Go to file

SevaSk 2c1986fd6d file clean up

2023-05-11 22:36:21 -04:00

speech_recognition

new speech_recognition

2023-05-11 22:20:49 -04:00

.gitignore

first commit

2023-05-07 22:10:48 -04:00

AudioRecorder.py

working now

2023-05-11 22:06:14 -04:00

AudioTranscriber.py

working now

2023-05-11 22:06:14 -04:00

GPTResponder.py

made clear work, response faster

2023-05-09 19:33:15 -04:00

main.py

file clean up

2023-05-11 22:36:21 -04:00

prompts.py

first commit

2023-05-07 22:10:48 -04:00

README.md

Create README.md

2023-05-11 22:08:52 -04:00

requirements.txt

Update requirements.txt

2023-05-11 22:07:37 -04:00

tiny.en.pt

first commit

2023-05-07 22:10:48 -04:00

README.md

ecoute

pip install -r requirments.txt from root

python setup.py install in speech_recognition

Description

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.

gpt-35-turbo whisper-ai windows

Readme MIT 197 MiB