CED Tiny Model CED are simple ViT Transformer based models for audio tagging, achieving sota performance on Audioset. Model Parameters (M) AS 20K (mAP) AS 2M (mAP) CED Tiny 5.5 36.5 48.1 CED Mini 9.6 38.5 49.0 CED Small 22 41.6 49.6 CED Base 86 44.0 50.0 Notable differences from other available models include: 1. Simplification for finetuning: Batchnormalization of Mel Spectrograms. During finetuning one does not need to first compute mean/variance over the dataset, which is common for AST. 1. Support for variable length inputs. Most other models use a static time frequency position embedding, which hinders the model's generalization to segments shorter than 10s. Many previous transformers simply pad their input to 10s in order to avoid the performance impact, which in turn slows down training/inference drastically. 1. Training/Inference speedup: 64 dimensional mel filterbanks and 16x16 patches without overlap, leading to 248 patches from a 10s spectrogram. In comparison, AST uses 128 mel filterbanks with 16x16 (10x10 overlap) convolution, leading to 1212 patches during training/inference. CED Tiny runs on a common CPU as fast as a comparable MobileNetV3. 1. Performance: CED with 1…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy