|
Download README.md from WJM-George/AMBIT: direct link, hf CLI and curl.
- Browser
- Download file 2.09 kB
-
https://huggingface.co/WJM-George/AMBIT/resolve/main/README.md
- Command line
-
hf download hf://WJM-George/AMBIT/README.md
-
curl -L -o README.md https://huggingface.co/WJM-George/AMBIT/resolve/main/README.md
2.09 kB
| license: mit | |
| pipeline_tag: text-to-audio | |
| tags: | |
| - spatial-audio | |
| - ambisonics | |
| - audio-editing | |
| - transfusion | |
| language: | |
| - en | |
| # AMBIT model checkpoint | |
| [Code and instructions](https://github.com/WJM-George/AMBIT) · [Demo](https://wjm-george.github.io/AMBIT/) · [Paper](https://arxiv.org/abs/2610.34415) | |
| AMBIT supports text-guided First-Order Ambisonics (FOA) generation and editing. Editing additionally takes reference FOA audio. | |
| One unified model supports both generation and editing. AR and DiT share the same Transformer backbone. All necessary model assets are included in the download. | |
| ## Use | |
| Requires Python 3.10+, Linux, and a CUDA GPU with bfloat16 support. | |
| Install the matching inference code, then download this repository: | |
| ```bash | |
| git clone https://github.com/WJM-George/AMBIT.git | |
| cd AMBIT | |
| python3 -m venv .venv | |
| source .venv/bin/activate | |
| python -m pip install -e . | |
| hf download WJM-George/AMBIT --local-dir models/AMBIT | |
| ``` | |
| Generation: | |
| ```bash | |
| python -m ambit.infer generate --bundle models/AMBIT \ | |
| --prompt "A dog barks to the left while a car passes from front to right." \ | |
| --output outputs/generated.wav --seed 42 | |
| ``` | |
| Editing: | |
| ```bash | |
| python -m ambit.infer edit --bundle models/AMBIT \ | |
| --source input_foa.wav \ | |
| --prompt "Move the dog to the right while keeping the other sounds unchanged." \ | |
| --output outputs/edited.wav --seed 42 | |
| ``` | |
| Both commands save FOA audio and the generated ScenePlan. Editing uses a 44.1 kHz, four-channel ACN/SN3D FOA reference in W, Y, Z, X order. | |
| ## Files | |
| - `model.safetensors`: shared Transformer, AR head, conditioning and AMBIT CLAP weights. | |
| - `vae.safetensors`: FOA audio encoder/decoder. | |
| - `bundle.json`, `renderer.json`, `vae.json`: inference configurations. | |
| - `codec/`: ScenePlan tokenization assets. | |
| - `planner_encoder/`, `text_encoder/`: text encoders and tokenizers. | |
| ## License and attribution | |
| AMBIT is distributed under the MIT license. Included third-party components | |
| retain their respective licenses; see `LICENSES/`. | |
| AMBIT builds on [stable-audio-tools](https://github.com/Stability-AI/stable-audio-tools). | |