AIbase
EN
Model Selection
Tags
Spectrogram Processing

# Spectrogram Processing

Ast Finetuned Audioset 16 16 0.442
Bsd-3-clause
An audio spectrogram transformer fine-tuned on the AudioSet dataset, utilizing a vision transformer architecture to process audio spectrograms, achieving excellent performance in audio classification tasks.
Audio Classification Transformers
A
MIT
35
1
Ast Finetuned Audioset 12 12 0.447
Bsd-3-clause
An Audio Spectrogram Transformer (AST) fine-tuned on the AudioSet dataset, using ViT architecture to process audio spectrograms, achieving excellent performance on multiple audio classification benchmarks.
Audio Classification Transformers
A
MIT
25
0
Ast Finetuned Audioset 10 10 0.448
Bsd-3-clause
An Audio Spectrogram Transformer (AST) fine-tuned on the AudioSet dataset, utilizing a vision transformer architecture to process audio spectrograms, achieving excellent performance in audio classification tasks.
Audio Classification Transformers
A
MIT
326
0
Ast Finetuned Audioset 10 10 0.450
Bsd-3-clause
An audio spectrogram transformer fine-tuned on the AudioSet dataset, utilizing ViT architecture for processing audio spectrograms, achieving excellent performance in audio classification tasks.
Audio Classification Transformers
A
MIT
109
4
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase