You can deploy this model and start earning money today!

amitpant7/
sam_audio_base_test

Views

No views yet

Audio Source Separation Blind Spots for Musical Instrument Segmentation

This dataset documents blind spots discovered in an audio source separation model when tested on various instrument isolation tasks.

Model Tested

SAM-Audio Base (Segment Anything Model for Audio) Model: facebook/sam-audio-base SAM-Audio is a foundation model for isolating sounds in audio using text, visual, or temporal prompts. I have evaluated the model’s text prompting capability for instrument… See the full description on the dataset page: https://huggingface.co/datasets/amitpant7/sam_audio_base_test.