All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog.
- New settings window to configure WhisperWriter.
- New main window to either start the keyboard listener or open the settings window.
- New continuous recording mode (Issue #40).
- New option to play a sound when transcription finishes (Issue #40).
- Migrated status window from using
tkinter
toPyQt5
. - Migrated from using JSON to using YAML to store configuration settings.
- Upgraded to latest versions of
openai
andfaster-whisper
, including support for local API (Issue #32).
- No longer using
keyboard
package to listen for key presses.
1.0.1 - 2024-01-28
- New message to identify whether Whisper was being called using the API or running locally.
- Additional hold-to-talk (PR #28) and press-to-toggle recording methods (Issue #21).
- New configuration options to:
- Choose recording method (defaulting to voice activity detection).
- Choose which sound device and sample rate to use.
- Hide the status window (PR #28).
- Migrated from
whisper
tofaster-whisper
(Issue #11). - Migrated from
pyautogui
topynput
(PR #10). - Migrated from
webrtcvad
towebrtcvad-wheels
(PR #17). - Changed default activation key combo from
ctrl+alt+space
toctrl+shift+space
. - Changed to using a local model rather than the API by default.
- Revamped README.md, including new Roadmap, Contributing, and Credits sections.
- Local model is now only loaded once at start-up, rather than every time the activation key combo was pressed.
- Default configuration now auto-chooses compute type for the local model to avoid warnings.
- Graceful degradation to CPU if CUDA isn't available (PR #30).
- Removed long prefix of spaces in transcription (PR #19).
1.0.0 - 2023-05-29
- Initial release of WhisperWriter.
- Added CHANGELOG.md.
- Added Versioning and Known Issues to README.md.
- Updated Whisper Python package; the local model is now compatible with Python 3.11.