This is a template repository for Audio to Audio to support generic inference with Hugging Face Hub generic Inference API. Examples of Audio to Audio are Source Separation and Speech Enhancement. There are two required steps:
- Specify the requirements by defining a
- Implement the
__call__methods. These methods are called by the Inference API. The
__init__method should load the model and preload all the elements needed for inference (model, processors, tokenizers, etc.). This is only called once. The
__call__method performs the actual inference. Make sure to follow the same input/output specifications defined in the template for the pipeline to work.
- Downloads last month