AudioLDM icon indicating copy to clipboard operation
AudioLDM copied to clipboard

Request for finetuned models on huggingface space

Open Bensolz opened this issue 2 years ago • 2 comments

Hi i was impressed by the capabilitys of the model demo on huggingface and then saw that there were finetuned versions of the models available so it would be nice if you could select these in the huggingface demo, also longer audio generation would be nice too

thank you for your consideration

Bensolz avatar May 07 '23 17:05 Bensolz

Sorry, we current do not have plans to put the fine-tuned model on to hugging face because we found it performs not so well. You are welcome to contribute though.

haoheliu avatar May 12 '23 20:05 haoheliu

ah i see thanks for the clarification good luck for development sadly i dont have the ressources to train my own models

Bensolz avatar May 13 '23 07:05 Bensolz