29/02/2024 | STANDALONE LiNUX WIN | 5.2 GB
英文简介：
A universe of possibilities powered by AI.
The ultimate voice cloning tool meticulously optimized for unrivaled power, modularity, and a user-friendly experience. Applio is the application that will allow us to create our own voices with AI or use existing voices. The program can be used installing it on your pc, or from the cloud through Google Colab (the best alternative for users who do not have a computer or have low resources).
Repository Enhancements
This repository has undergone significant enhancements to improve its functionality and maintainability:
Modular Codebase: Restructured codebase following a modular approach for better organization, readability, and maintenance.
Hop Length Implementation: Implemented hop length, courtesy of @Mangio621, boosting efficiency and performance, especially on Crepe (formerly Mangio-Crepe).
Translations in 30+ Languages: Added support for translations in over 30 languages, enhancing accessibility for a global audience.
Cross-Platform Compatibility: Ensured seamless operation across various platforms for a consistent user experience.
Optimized Requirements: Fine-tuned project requirements for enhanced performance and resource efficiency.
Streamlined Installation: Simplified installation process for a user-friendly setup experience.
Hybrid F0 Estimation: Introduced a personalized 'hybrid' F0 estimation method utilizing nanmedian, combining F0 calculations from various methods to achieve optimal results.
Easy-to-Use UI: Implemented a user-friendly interface for intuitive interaction.
Optimized Code & Dependencies: Enhanced code and streamlined dependencies for improved efficiency.
Plugin System: Introduced a plugin system for extending functionality and customization.
These enhancements contribute to a more robust and scalable codebase, making the repository more accessible for contributors and users alike.
Installation:
Download the zip file, extract it, then:
open the 'run-applio.bat' file (Windows)OR
chmod +x run-applio.sh ./run-applio.sh .(Linux).OR
Using Makefile (for platforms such as Paperspace)
make run-applio
Changelog:
v3.0.8
Changes
New and enhanced Voice Blender option, now available again better than ever.
The upcoming Applio update includes detailed descriptions of all parameters, both in training and inference, providing clarity on actions and their impact on results.
An advanced audio cleaning system is introduced, highly recommended for improving the clarity of spoken audio or text-to-speech (TTS).
Additional inference options, driven by community feedback, will also be incorporated.
Inference times reduced! We optimized the code to make inference much faster!
Stop training directly on the web ui.
General Fixes.Planned Features
Implement: Support for Apple Devices (Issue Link)
Implement: rmvpe_gpu
Implement: Overtraining detector
官网: https://github.com/IAHispano/Applio
评论0