Instructions to use Zyphra/ZONOS3-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Zonos
How to use Zyphra/ZONOS3-Mini with Zonos:
# 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("Zyphra/ZONOS3-Mini", 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) - Notebooks
- Google Colab
- Kaggle
Download registries/codec_registry_keep2_plain.json from Zyphra/ZONOS3-Mini: direct link, hf CLI and curl.
- Browser
- Download file 565 Bytes
-
https://huggingface.co/Zyphra/ZONOS3-Mini/resolve/main/registries/codec_registry_keep2_plain.json
- Command line
-
hf download hf://Zyphra/ZONOS3-Mini/registries/codec_registry_keep2_plain.json
-
curl -L -o codec_registry_keep2_plain.json https://huggingface.co/Zyphra/ZONOS3-Mini/resolve/main/registries/codec_registry_keep2_plain.json
565 Bytes
| { | |
| "3n_600k_sched600k_r4096": { | |
| "key": "3n_600k_sched600k_r4096", | |
| "codec": "opus_dual_3n_600k_sched600k_r4096_step600000", | |
| "family": "dual", | |
| "codebooks": 10, | |
| "codebook_sizes": [ | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096 | |
| ], | |
| "hop": 2940, | |
| "frame_rate": 15.0, | |
| "codec_step": 600000, | |
| "checkpoint": "autoencoder/generator.pt", | |
| "decoder": { | |
| "kind": "istft_mr", | |
| "campaign": "autoencoder/heads/keep2_plain", | |
| "checkpoint": "step_0050000.pt", | |
| "expect_step": 50000, | |
| "headroom_db": 3.0 | |
| } | |
| } | |
| } | |