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.
Go to file
2023-05-12 22:42:38 -04:00
custom_speech_recognition renamed to custom speech recognition 2023-05-12 10:54:28 -04:00
.gitignore update requirements 2023-05-12 12:00:03 -04:00
AudioRecorder.py Refactor 2023-05-12 22:42:38 -04:00
AudioTranscriber.py Refactor 2023-05-12 22:42:38 -04:00
GPTResponder.py made clear work, response faster 2023-05-09 19:33:15 -04:00
main.py Refactor 2023-05-12 22:42:38 -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 added transcript limit 2023-05-12 21:08:31 -04:00
tiny.en.pt first commit 2023-05-07 22:10:48 -04:00

ecoute

pip install -r requirments.txt from root

python setup.py install in speech_recognition