[Discussion] Pretrained Spleeter models as layer in a Keras model

Is it possible to use the pretrained Spleeter models as a layer in a tensorflow keras model built with the functional api?

I currently use Spleeter in my preprocessing pipeline for a CRNN classifier, but I had the idea to move it into my model instead of doing the source separation beforehand.

```
┌───────┐ ┌──────────┐ ┌────────────┐
│ Input ├────►│ Spleeter ├────►│ Classifier │
└───────┘ └──────────┘ └────────────┘
```

The issue mentions pretrained Spleeter models, TensorFlow Keras, the functional API, and a CRNN classifier, but names no files, tests, or entry points. First determine whether the pretrained models can be integrated as a Keras layer in that pipeline. Done would require a clear feasibility result and an agreed implementation scope.

Written by the indexing model from the issue text.