Is there too little data for clustering？

zhvng / open-musiclm

Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.

https://arxiv.org/abs/2301.11325

MIT License

511 stars 59 forks source link

Closed lzl1456 closed 1 year ago

lzl1456 commented 1 year ago

it's only about 80 hours，I'm not sure if the actual training was changed

"hubert_kmeans_trainer_cfg": { "folder": "./data/fma_large", "feature_extraction_num_steps": 320, "feature_extraction_batch_size": 32 },