You can deploy this model and start earning money today!

eugenehp/
zipvoice

Name: zipvoice
Rating: 2.5 (6 reviews)

Views

No views yet

ZipVoice ONNX (RLX staging)

ZipVoice ONNX text encoder + flow decoder for RLX.

Field	Value
Hub id	`eugenehp/zipvoice`
Kind	Converted / re-laid-out for RLX from an upstream checkpoint.
RLX crate	`rlx-zipvoice`
Upstream	https://huggingface.co/k2-fsa/ZipVoice

bash

hf download eugenehp/zipvoice --local-dir .
cargo run -p rlx-zipvoice --release -- --model-dir .

fm_decoder.onnx (455.3 MiB)
zipvoice.f16.gguf (267.9 MiB)
onnx/vocoder_spec.onnx (51.6 MiB)
text_encoder.onnx (16.8 MiB)
encoder_body.onnx (16.8 MiB)
tokens.txt (2.5 KiB)

These files may be present for historical / staging reasons but are not the supported RLX load path:

Community *.f16.gguf / LM-only Q4 packs are format wraps — they are not drop-in replacements for the RLX primary file above.

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

cargo run -p rlx-zipvoice --release -- --model-dir .

Apache License 2.0 — see LICENSE. Inherit upstream terms when redistributing.

Cards and LFS attrs are regenerated from the local weights/ tree in rlx-models via python3 scripts/prepare_weights_hf.py.