OpenInterpreter
Speech recognition
Describe the changes you have made:
Added support for google's online speech recognition.
terminal_inerface.py: Changed code execution prompt to words yes and no which get folded into y, n. e for edit wasn't in the original prompt, but gets folded anyway. Changed simple input call for y/n to cli_input() to allow for voice control.
cli_input.py: Lazy library loading with installation instructions upon failure. Changed prompts to remain on one line instead of scrolling.
README.md: Updated available chat commands and linked to documentation for google.
A separate file in docs/ was not created. Libraries were not added to poetry. I am new to it and didn't want to play with conditional installation if people don't care about STT. SpeechRecognition and pyaudio are used which may require running apt or brew.
Reference any relevant issues (e.g. "Fixes #000"):
Pre-Submission Checklist (optional but appreciated):
- [ x] I have included relevant documentation updates (stored in /docs)
- [ x] I have read
docs/CONTRIBUTING.md - [ x] I have read
docs/ROADMAP.md
OS Tests (optional but appreciated):
- [ ] Tested on Windows
- [ x] Tested on MacOS
- [ ] Tested on Linux
Hey @CodeAKrome Thanks for the PR!
I'd like users to be able to choose their STT option. I personally would prefer to use a local option instead of using Google, as I'm sure is the case for many in the open source community.
