Download tune-crepe-tiny-float32.aimodel/metadata.json from arraypress/tune-crepe: direct link, hf CLI and curl.
- Browser
- Download file 480 Bytes
-
https://huggingface.co/arraypress/tune-crepe/resolve/main/tune-crepe-tiny-float32.aimodel/metadata.json
- Command line
-
hf download hf://arraypress/tune-crepe/tune-crepe-tiny-float32.aimodel/metadata.json
-
curl -L -o metadata.json https://huggingface.co/arraypress/tune-crepe/resolve/main/tune-crepe-tiny-float32.aimodel/metadata.json
480 Bytes
| { | |
| "license" : "MIT", | |
| "author" : "Kim, Salamon, Li, Bello — CREPE (ISMIR 2018); PyTorch weights via torchcrepe (Max Morrison); Core AI export by PitchTracker", | |
| "assetVersion" : "2.0", | |
| "creationDate" : "20260924T120849Z", | |
| "description" : "CREPE tiny: [256, 1024] normalised 16 kHz frames → [256, 360] sigmoid activations over 20-cent bins from 1997.38 cents (32.7 Hz). Framing and decoding in the host as marl\/crepe does them.", | |
| "producer" : "coreai-core 1.0.0b2" | |
| } |