Skip to content

Activity

Showing most recent first

Fixed link to paper in README

liamduganpushed 1 commit to main • c4773af…6425e2a • 
on Jan 14

Fixed paper link in README

liamduganpushed 1 commit to main • dac82d6…c4773af • 
on Sep 1, 2023

Added install instructions for venv

liamduganpushed 1 commit to main • 89fb37d…dac82d6 • 
on Sep 1, 2023

Merge pull request #1 from zhudotexe/main

Pull request merge
liamduganpushed 5 commits to main • e271ffd…89fb37d • 
on Aug 26, 2023

Deleted branch

liamdugandeleted liam • 
on Aug 24, 2023

Added README and updated getting started

liamduganpushed 1 commit to main • 963c9d5…e271ffd • 
on Aug 24, 2023

Removed verbose cli arg and added comments

liamduganpushed 1 commit to main • af2b726…963c9d5 • 
on Aug 23, 2023

Fixed bug in how we call print transcription

liamduganpushed 1 commit to main • 9cb33b4…af2b726 • 
on Aug 23, 2023

Cleaned up console prints

liamduganpushed 1 commit to main • 7fe091a…9cb33b4 • 
on Aug 23, 2023

Added listing of microphones when mic error happens

liamduganpushed 1 commit to main • 5a3615b…7fe091a • 
on Aug 22, 2023

Added spoken transcript as prompt and refactored microphone config

liamduganpushed 1 commit to main • 171205e…5a3615b • 
on Aug 22, 2023

Simplified logic and removed spoken audio from whisper queries

liamduganpushed 1 commit to main • 0abb4a2…171205e • 
on Aug 22, 2023

Changed recognize process creation logic

liamduganpushed 1 commit to main • 6dff321…0abb4a2 • 
on Aug 22, 2023

Separated out vocalizer logic from main python file

liamduganpushed 1 commit to main • af3ce30…6dff321 • 
on Aug 22, 2023

Moved policy translator and recorder into separate subfolder modules

liamduganpushed 1 commit to main • 4b49477…af3ce30 • 
on Aug 22, 2023

Separated out Policy logic

liamduganpushed 1 commit to main • 884f416…4b49477 • 
on Aug 16, 2023

removed catch for keyboard interrupt and changed input parser

liamduganpushed 1 commit to main • d45cfe2…884f416 • 
on Aug 16, 2023

Shifted more functionality to recorder

liamduganpushed 1 commit to main • 8d3a934…d45cfe2 • 
on Aug 16, 2023

Separate out recorder logic from main file

liamduganpushed 1 commit to main • 79acc93…8d3a934 • 
on Aug 16, 2023

removed safe_load for yaml and moved elevenlabs header construction

liamduganpushed 1 commit to main • 930570e…79acc93 • 
on Aug 16, 2023

Added more options to config file

liamduganpushed 1 commit to main • 55fffbe…930570e • 
on Aug 16, 2023

Renamed to frame width and adjusted default overlap tolerance

liamduganpushed 1 commit to main • cbda905…55fffbe • 
on Aug 16, 2023

Moved recorder config to config.yml

liamduganpushed 1 commit to main • 2fd5354…cbda905 • 
on Aug 16, 2023

Added support for API whisper

liamduganpushed 1 commit to main • 7100b11…2fd5354 • 
on Aug 16, 2023

Moved pipeline.py to evaluation and separated out eval metrics

liamduganpushed 3 commits to main • 245e3cf…7100b11 • 
on Aug 15, 2023

Fixed bug in consensus threshold

liamduganpushed 1 commit to main • f845d4a…245e3cf • 
on Apr 12, 2023

Added CLI options and policy flags

liamduganpushed 1 commit to main • 65571bf…f845d4a • 
on Apr 12, 2023

Merge branch 'main' of github.com:liamdugan/speech-to-speech

liamduganpushed 2 commits to main • 5ac8c13…65571bf • 
on Apr 11, 2023

Updated README with new repo name

liamduganpushed 1 commit to main • 859f7bf…5ac8c13 • 
on Apr 10, 2023

Add experiment pipeline

liamduganpushed 3 commits to main • dfa5137…859f7bf • 
on Apr 10, 2023