Kokoro-82M ONNX (RLX staging)

Kokoro-82M ONNX + voice embeddings for RLX.

Field Value
Hub id eugenehp/kokoro-82m
Kind Staging redistrib of an upstream checkpoint for RLX runners.
RLX crate rlx-kokoro
Upstream https://huggingface.co/onnx-community/Kokoro-82M-v1.0-ONNX

Quick start

hf download eugenehp/kokoro-82m --local-dir .
cargo run -p rlx-kokoro --release -- --model . --voice af_heart

File highlights

  • onnx/model.onnx (310.5 MiB)
  • onnx/rlx-split/decoder_raw.onnx (235.7 MiB)
  • kokoro-82m-q8_0.gguf (134.8 MiB)
  • onnx/rlx-split/encoder.onnx (74.7 MiB)
  • tokenizer.json (3.4 KiB)
  • tokenizer_config.json (113 B)
  • config.json (44 B)

Run with RLX

Clone rlx-models, place this repo under weights/tts/kokoro-82m (or pass the path explicitly), then:

cargo run -p rlx-kokoro --release -- --model . --voice af_heart

License

Apache License 2.0 โ€” see LICENSE. Inherit upstream terms when redistributing.

Original weights and authorship: https://huggingface.co/onnx-community/Kokoro-82M-v1.0-ONNX

Redistrib note

This Hub repo exists so RLX recipes have a stable fetch target. When you only need the upstream checkpoint, prefer the Upstream link above.

Downloads last month
96
GGUF
Model size
81.7M params
Architecture
kokoro
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support