Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
ONNX files exported from Kokoro 1.1-zh. Voices have been converted to HDF5 and the speed input now uses type float32 (originally int64).
Model source
Source description
ONNX files exported from Kokoro 1.1-zh. Voices have been converted to HDF5 and the speed input now uses type float32 (originally int64).
Sources
1 sourceVerified Sep 21
Model artifacts
64 artifactsSource excerpts
2 excerpts--- base_model: - hexgrad/Kokoro-82M-v1.1-zh pipeline_tag: text-to-speech tags: - onnx --- # Kokoro 1.1-zh [ONNX] ONNX files exported from [Kokoro 1.1-zh](https://huggingface.co/hexgrad/Kokoro-82M-v1.1-zh). Voices have been converted to HDF5 and the `speed` input now uses type `float32` (originally `int64`).
voices/af_sol.h5
h5 · 516 KB · SHA-256 95bee82ff282…143e · Hugging Face
Source context: 8 downloads · 0 likes · Pipeline text-to-speech · Repo alexisStacksCode/Kokoro-1.1-zh-ONNX
