Spaces:
Paused
Paused
Commit History
-
Security: Add env-example.txt with placeholder token
- Add back env-example.txt with placeholder instead of real token - File was removed from history to eliminate security risk1d459db -
Security: Remove committed HF token and add .gitignore
- Remove .env file containing real Hugging Face token from repository - Add .gitignore to prevent future accidental commits of sensitive files - Token should be set via environment variables or Hugging Face Spaces secrets2a86c4a -
Update environment example and Dockerfile health check
- Changed HF_TOKEN placeholder in env-example.txt for better clarity. - Updated health check command in Dockerfile to verify server response correctly. - Adjusted parameter name in app.py for audio generation to align with model requirements.f3c8dbf -
Refactor application to integrate AudioLDM2 model
- Replaced Stable Audio model with AudioLDM2 for text-to-audio generation. - Updated model loading and generation functions to accommodate new model parameters. - Modified Dockerfile to use Python 3.11 and added GPU support for better performance. - Enhanced health check mechanism and application startup messages. - Updated README to reflect changes in model and usage instructions.a82c7f0 -
Add Hugging Face authentication and update server port
- Implemented environment variable loading with dotenv for Hugging Face token. - Added Hugging Face authentication logic in app.py with error handling. - Updated README with setup instructions for Hugging Face authentication. - Changed server port from 7860 to 8080 in app.py. - Added huggingface_hub and python-dotenv to requirements.txt.fa03fad -
Update compiled Python bytecode for app module
2a22076 -
Implement Stable Audio model integration
- Add Stable Audio Open model (stabilityai/stable-audio-open-small) - Implement model loading with caching mechanism - Add PyTorch, diffusers, transformers dependencies - Update Dockerfile for Hugging Face Spaces deployment - Add comprehensive error handling and fallback mechanisms - Update README with model informationd0fa7b7 -
Refactor Dockerfile for lightweight audio synthesis
Updated the Dockerfile to use a slim Python 3.10 image, streamlined system dependencies for audio processing, and removed CUDA support for PyTorch. Added a health check to ensure application stability. This change optimizes the Docker image for audio synthesis tasks.a611150 -
Enhance error handling in audio generation
Updated the seed input validation in the generate_audio_from_prompt function to include OverflowError, ensuring that cases like infinity are handled gracefully. This change improves the robustness of the audio generation process by providing a fallback to system entropy when the seed is invalid.84525fb -
Improves audio generation robustness
Adds input validation and sanitization to audio generation functions to prevent errors caused by invalid or unexpected inputs. Handles potential errors gracefully with fallback mechanisms, including a simplified audio tone as a last resort, enhancing the application's stability and user experience. Also, adds limits to the random seed input to prevent errors.88a32e8
-
Fix remaining merge conflict marker in README.md
c8c916d -
Resolve merge conflicts: Keep lightweight synthesis version
f86e88f -
Implement audio generation functionality with simple synthesis and fallback mechanism; update requirements to remove unused libraries.
e911600
-
Update app.py and README.md: Enhance local launch configuration for Docker support and update documentation to include Docker deployment instructions.
2276588 -
Enhance app.py: Implement GPU acceleration for model loading and audio generation; refactor generate_audio function for improved error handling and fallback mechanisms.
5715d51 -
Refactor app.py: Create Gradio demo for Hugging Face Spaces and update launch method; Update requirements.txt to include Gradio dependency
48924fc
-
Update requirements: Add missing dependencies for audio processing and improve documentation
99bda05 -
Fix build error: Remove gradio from requirements.txt to avoid version conflict
c30d48f -
Fix build error: Use stable-audio-open-small model with better error handling
f9d8177 -
Integrate Stable Audio Open 1.0 model for real audio generation
e84dfd0 -
Initial setup: Add Stable Audio Gradio app with interface, requirements, and updated README
fff9bbe -
Initial setup: Add Stable Audio Gradio app with interface, requirements, and updated README
505eff0 -
initial commit
c64278a