| VocoLoco ONNX and WebGPU engine files (https://huggingface.co/Gigsu/vocoloco-onnx) | |
| engine/decoder-f32.*, engine/encoder-f32.*, omnivoice-decoder.onnx and | |
| omnivoice-encoder-fixed.onnx are converted from the Higgs Audio v2 tokenizer by | |
| Boson AI, as shipped in k2-fsa/OmniVoice (audio_tokenizer/), under the Boson | |
| Higgs Audio 2 Community License (LICENSE-higgs-audio-2), which is based on the | |
| Meta Llama 3 Community License (LICENSE-llama-3). | |
| Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. | |
| Boson Higgs Audio 2 is licensed under the Boson Community License, Copyright © Boson AI USA, Inc. All Rights Reserved. | |
| Built with Higgs Materials licensed from Boson AI USA, Inc., Copyright Boson AI | |
| USA, Inc., All Rights Reserved and Meta Llama 3 licensed under the Meta Llama 3 | |
| Community License, Copyright Meta Platforms, Inc., All Rights Reserved. | |
| The OmniVoice main model files (engine/omnivoice-f16.*, omnivoice-main-split.onnx | |
| and its data shards) are converted from k2-fsa/OmniVoice by Xiaomi Corp., | |
| licensed CC BY-NC (https://huggingface.co/k2-fsa/OmniVoice#license). | |