AI NEWS.ccBreeze-TTS-2.cpp
GGUF conversions of BreezeBlue/Breeze-TTS-2 for **Breeze-TTS-2.cpp**, a C++ reimplementation running on ggml with a Vulkan backend, so it works on NVIDIA, AMD and Intel GPUs and falls back to CPU. These files will not load in llama.cpp. They need the Breeze-TTS-2.cpp runtime, which implements all four stages of the model: the T5Gemma2 text encoder, the Qwen3 backbone, the 15 step depth decoder and the vocoder. Everything except the `-dd` files keeps the depth decoder at higher precision than the rest of the model. The `-dd` variants quantize it too, which is why they are smaller.
译文尚未就绪，显示来源原文
GGUF conversions of BreezeBlue/Breeze-TTS-2 for **Breeze-TTS-2.cpp**, a C++ reimplementation running on ggml with a Vulkan backend, so it works on NVIDIA, AMD and Intel GPUs and falls back to CPU. These files will not load in llama.cpp. They need the Breeze-TTS-2.cpp runtime, which implements all four stages of the model: the T5Gemma2 text encoder, the Qwen3 backbone, the 15 step depth decoder and the vocoder. Everything except the `-dd` files keeps the depth decoder at higher precision than the rest of the model. The `-dd` variants quantize it too, which is why they are smaller.