Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Continuous mode not working #148

Closed
wants to merge 40 commits into from
Closed

Conversation

vivekuppal
Copy link

Continuous mode broke after UI changes accidentally changed one of the parameters for a button.

vivekuppal and others added 30 commits June 29, 2023 08:58
Update readme for addition of new models.
Update license agreement for Transcribe.
Add linting.
Code clean up
* Show all text in chronological order instead of current behavior of showing only the last MAX_PHRASES(10) items. Use the last MAX_PHRASES(10) for generating a response to the conversation.

* Remove print statements, debugging code.

* Remove references to Git LFS. Add a note about models.
* Save conversation to text.

* Allow users to customize the prompts and get contextual responses.

* Update readme with feature request for Contextual information.

* Update button text.
Resolves issue #14
Fix links for download of the models.
code reorg to separate some of the UI code
* Add support for multi languages.
- Add script for generation of binaries
- Separate transcription related vars into a singleton global class
- Further remove ui code from main.py class
- Add a File, Edit menu
Disable winrar UI
…arameter in the method (#24)

When using --api option, get an error when running transcribe.
* sorted Language combobox
* small fix
* Generate binaries and put them on github
* Update Readme for generated binaries
Add a parameters.yaml for configurable parameters
Allow specification of api key as a command line arg
Add api key to parameters.yaml file
Api key specified in cmd line args take precedence over parameters.yaml file
Create a base Singleton class
Implement Config object (Singleton) for reading from parameters file
Redo implementation of Transcription Globals class as Singleton using Singleton base class
Add parameters.yaml file to installer zip for installed version of Transcribe
Update Readme with instructions for using API key.
--api option was not working correctly even when a good API key was provided.

For transcription local models are working well.
When using --api option and attempting to transcribe using openAI API transcription was not happening because incorrect API Key was being sent to the API.
* Do not ping LLM if we do not need to. Previously we were always pinging LLM even when response suggestions were off. Partial refactoring work towards separating the conversation its own object.

* Make openai model configurable using parameters.yaml so it is easy to change for end user.
- Add feature to get response from LLM on demand in addition to getting it continuously. 
This option is very useful when continuous response from LLM is disabled.
- Bug Fix: Pausing, restarting transcription was not working from File Menu.
* Add links to the official site
vivekuppal and others added 10 commits July 31, 2023 20:04
* List all audio drivers, devices(speakers, microphone) on the machine.
* Add info about the mic, speaker in use currently.
Allow user to select non default speaker, microphone using command line arguments.
List of devices can be obtained using the -l option
* Allow selective enabling, disabling of mic, speaker using command line arguments.
* Update readme with features.
* Add text to speech. Parse OpenAI responses better than before
Create new binaries till this version and update Readme file with link to the new binaries.
* multiturn prompts, bug fixes
* updated the gdrive link to the latest version
* ui additions for enable/disable functionality
@vivekuppal vivekuppal closed this Sep 8, 2023
@vivekuppal vivekuppal deleted the vu-issue-59 branch September 8, 2023 14:51
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants