Fetching metadata from the HF Docker repository...
-
fix: correct audio buffer handling in full text processing response
-
fix: update explanation generation model to mistral-medium-2505
-
feat: add FULL_TEXT_TTS_ENDPOINT to environment variables
-
feat: implement simplified audio processing with enhanced TTS API integration
-
api updated
-
fix: downgrade click package version to 8.1.7
-
api docs and code added
-
docs: enhance README with detailed application overview, features, and installation instructions
-
fix: update video link in README to point to the correct overview
-
fix: update command in tasks.json to correct app.py path
-
fix: add soundfile package to requirements
-
fix: update import path for TextExplainer to reflect new structure
-
fix: update app_file path in README to reflect correct location
-
removed old code
-
docs: update README to include video overview section
-
fix: update websockets version constraint to allow compatible versions
-
Revert "feat: implement AudioConcatenator package with audio processing utilities"
This reverts commit 9274377d1e8d682214a22725451e1033b67391ef. -
Revert "fix: update websockets version constraint for compatibility"
This reverts commit c9078b4d26da0d9966124e20a902c137fa3d950c. -
feat: implement AudioConcatenator package with audio processing utilities
-
fix: update websockets version constraint for compatibility
-
fix: downgrade tomlkit version to 0.12.0 for compatibility
-
fix: update pillow version constraint to allow compatible versions
-
fix: remove MarkupSafe dependency from requirements.txt
-
fix: remove gradio_client dependency from requirements.txt
-
fix: downgrade aiofiles version to 23.2.1 for compatibility
-
fix: downgrade gradio version to 4.36.0 for compatibility
-
fix: update app_file path in README to reflect new directory structure
-
fix: downgrade python-dotenv to version 1.1.0 for compatibility
-
feat: Update audio processing to support parallel chunking and enhance text chunking logic
-
feat: Add VSCode task to activate virtual environment and run app.py
-
feat: Remove text truncation logic from audio generation process
-
new app
-
feat: Update PDF processing to improve status updates during audio generation
-
feat: Enhance PDF processing to automatically extract text, generate explanations, and produce audio
-
feat: Add explanation generation and audio output features to PDF extractor
-
feat: Load environment variables at the start of the application
-
feat: Enhance PDF extraction interface with improved layout and error handling
-
feat: Initialize PDF upload functionality with Gradio interface
-
feat: Improve TTS audio generation with enhanced progress tracking and error handling
-
feat: Simplify interface by removing unused buttons and status outputs
-
feat: Add TTS audio generation for explanations and improve error handling
-
chatterbox imported
-
feat: Enhance explanation prompts for clarity and relevance
-
feat: Include chat history in the explain text response
-
feat: Filter out placeholder explanations in display formatting
-
feat: Simplify explanation formatting by concatenating explanations for display
-
refactor: Remove unnecessary blank lines in create_dummy_interface function
-
feat: Skip API call for short content and log to chat history for context
-
feat: Enhance topic extraction in TextExplainer with structured output and improved context handling
-
feat: Enhance TextExplainer to maintain chat history for contextual explanations
