Instructions to use LetATechLtd/kokoro-82m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use LetATechLtd/kokoro-82m with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=LetATechLtd/kokoro-82m \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
Mellions Kokoro voice bundle
mellions_kokoro_en_fr.litertlm is the on-device voice of the Mellions app: a trimmed copy of
litert-community/Kokoro-82M's
kokoro_int8_gpu_fp16.litertlm (revision 33ad69fec6c4d9eb10a547aaf9a8c63e7c446a56), run with
MediaPipe Tasks Audio 1.2.0.
| File | Bytes | SHA-256 |
|---|---|---|
mellions_kokoro_en_fr.litertlm |
133,969,920 | e652e4cf36ad1e1f1d20ad504cea464ec6424ffc54a780b103893b1cb644b04e |
Voices:
af_heart(Sophia, English)am_michael(Marc, English)af_alex(Alex, English): the element-wise mean ofaf_heartandam_michaelff_siwis(Sophia, French)
Languages: en-US, en-GB and fr-FR.
The bundle is rebuilt byte for byte from a lock that pins the source file, every builder package by hash, the
recipe and the header. NOTICE lists every change to the upstream file. Licensed under the Apache License 2.0
(LICENSE).
- Downloads last month
- 29