### Install Environment Dependencies Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Commands to create a Conda environment and install required Python packages and system dependencies. ```bash conda create -n anyaccomp python=3.9 conda activate anyaccomp conda install -c conda-forge ffmpeg=4.0 pip install -r requirements.txt ``` -------------------------------- ### Clone the Repository Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Initial steps to download the source code and navigate to the project directory. ```bash git clone https://github.com/AmphionTeam/AnyAccomp.git # enter the repositry directory cd AnyAccomp ``` -------------------------------- ### Run Gradio Playground Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Launch the local web interface for interacting with the model. ```bash python gradio_app.py ``` -------------------------------- ### Download Pretrained Models Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Commands to download model weights from Hugging Face, with an optional mirror endpoint for connectivity issues. ```bash python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='amphion/anyaccomp', local_dir='./pretrained', repo_type='model')" ``` ```bash export HF_ENDPOINT=https://hf-mirror.com ``` -------------------------------- ### Download Pretrained Checkpoints with Python Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Use the huggingface_hub library to programmatically download model checkpoints. ```python from huggingface_hub import hf_hub_download # download semantic codec ckpt semantic_code_ckpt = hf_hub_download("amphion/anyaccomp", filename="") # same for other models ``` -------------------------------- ### Configure HuggingFace Mirror Endpoint Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Set the environment variable to use a mirror site if direct connection to HuggingFace is unstable. ```bash export HF_ENDPOINT=https://hf-mirror.com ``` -------------------------------- ### Run Batch Inference Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md Execute the inference script to process audio files from a specified folder. ```bash python infer_from_folder.py ``` -------------------------------- ### Cite AnyAccomp Research Source: https://github.com/amphionteam/anyaccomp/blob/main/README.md BibTeX entry for referencing the AnyAccomp paper in academic work. ```bibtex @article{zhang2025anyaccomp, title={AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck}, author={Zhang, Junan and Zhang, Yunjia and Zhang, Xueyao and Wu, Zhizheng}, journal={arXiv preprint arXiv:2509.14052}, year={2025} } ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.