--- license: apache-2.0 tags: - text-to-speech - tts - onnx - onnxruntime - webgpu - vulkan - voice-cloning - fp16 - kv-cache language: - multilingual library_name: onnxruntime base_model: k2-fsa/OmniVoice --- # OmniVoice WebGPU FP16 KV B1 ONNX Bundle This repository contains the model bundle used by OmniVoice Vulkan Bridge. The main diffusion model is the fp16, KV-cached, B=1 split ONNX export. Bridge code: [MarkShark2/omnivoice-vulkan-bridge](https://github.com/MarkShark2/omnivoice-vulkan-bridge) ## Model Notes - Base model: `k2-fsa/OmniVoice` - Main graph: fp16, KV-cached, B=1 split conditional/unconditional CFG passes - Decoder: WebGPU-compatible graph surgery for ONNX Runtime Web 1.25 prerelease - Encoder: WebGPU-capable voice-reference encoder with WASM fallback in the bridge ## Attribution Based on OmniVoice by k2-fsa and Xiaomi Corp. The original inference code for this project was based on [Magkino/vocoloco_tts](https://github.com/Magkino/vocoloco_tts).
