Instructions to use wdga/kokoro-82m-litert-runtime-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use wdga/kokoro-82m-litert-runtime-preview with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| Kokoro 82M LiteRT Decoder/Vocoder Preview | |
| This package contains a converted LiteRT/TFLite decoder-vocoder artifact derived | |
| from the Kokoro 82M model: | |
| Source model: https://huggingface.co/hexgrad/Kokoro-82M | |
| Source file: kokoro-v1_0.pth | |
| License: Apache License 2.0 | |
| The conversion was produced from the robot edge-runtime research repository: | |
| Repository: https://github.com/will-deines/robot | |
| Commit: bb72dce | |
| The generated artifact contains a custom operator named KokoroSourceStft. The | |
| package includes Linux x86-64 and cross-compiled Linux aarch64 shared objects. | |
| Other platforms should rebuild the custom operator from the included C++ source. | |
| This package is not endorsed by the Kokoro authors, Hugging Face, Google, | |
| LiteRT, TensorFlow, or Pollen Robotics. | |