Models
Confucius4-TTS
netease-youdao/Confucius4-TTS
Confucius4-TTS is an open multilingual, cross-lingual zero-shot text-to-speech model that clones a speaker's voice across 14 languages while preserving emotion and identity.
Topics
Related projects
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.
descript-audio-codec1.9kDescript's neural audio codec model, released with weights plus training and inference scripts. It compresses 44.1 kHz audio at very low bitrates while preserving fidelity.
peft21.9kA Python library for parameter-efficient fine-tuning like LoRA, adapting large pretrained models by training only small adapters.
kornia12.3kA differentiable computer vision library built on PyTorch for image processing, geometric vision, and augmentation pipelines.
cleanrl10.7kHigh-quality single-file deep RL library covering PPO, DQN and SAC, focused on readability and reproducible experiment management.
techniques10.3kA curated index of deep-learning techniques for satellite and aerial imagery, organizing external repos and papers by classification, segmentation and detection tasks.