Zonos-v0.1 transformer (RLX staging)
Zyphra Zonos-v0.1 transformer weights for RLX.
| Field | Value |
|---|---|
| Hub id | eugenehp/zonos |
| Kind | Staging redistrib of an upstream checkpoint for RLX runners. |
| RLX crate | rlx-zonos |
| Upstream | https://huggingface.co/Zyphra/Zonos-v0.1-transformer |
Quick start
hf download eugenehp/zonos --local-dir .
cargo run -p rlx-zonos --release -- --model-dir .
File highlights
model.safetensors(3.0 GiB)zonos-v0.1-transformer-f16.gguf(3.0 GiB)config.json(2.5 KiB)
Run with RLX
Clone rlx-models, place this repo under weights/tts/zonos (or pass the path explicitly), then:
cargo run -p rlx-zonos --release -- --model-dir .
License
Apache License 2.0 — see LICENSE. Inherit upstream terms when redistributing.
Original weights and authorship: https://huggingface.co/Zyphra/Zonos-v0.1-transformer
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
- 56
# pip install git+https://github.com/Zyphra/Zonos.git import torchaudio from zonos.model import Zonos from zonos.conditioning import make_cond_dict model = Zonos.from_pretrained("eugenehp/zonos", device="cuda") wav, sr = torchaudio.load("speaker.wav") # 5-10s reference clip speaker = model.make_speaker_embedding(wav, sr) cond = make_cond_dict(text="Hello, world!", speaker=speaker, language="en-us") codes = model.generate(model.prepare_conditioning(cond)) audio = model.autoencoder.decode(codes)[0].cpu() torchaudio.save("sample.wav", audio, model.autoencoder.sampling_rate)