Linus Ostberg

The following example doesn't work: ```python from musicnn.extractor import extractor taggram, tags = extractor('./audio/joram-moments_of_clarity-08-solipsism-59-88.mp3', model='MTT_musicnn') ~~~~ ``` Since the `extract_features` parameter defaults to `True`, it produces a "too many values...

I ran into legacy errors when there was an upper bound on NumPy, as later versions of Librosa require NP >= 17. * Librosa `Version: 0.9.2` * NumPy `Version: 1.23.3`...

[Feat]: Batch Prediction and Cached Prompt should work together

2

### Is your feature request related to a problem? Please describe. Batch predictions should be able to use a cached context. ### Describe the solution you'd like We are currently...