AST

Implementation of AST from the paper: "AST: Audio Spectrogram Transformer' in PyTorch and Zeta. In this implementation we basically take an 2d input tensor representing audio -> then patchify it -> linear proj -> then position embeddings -> then attention and feedforward in a loop for layers. Please Join Agora and tag me if this could be improved in any capacity.

Install

pip3 install ast-torch

Usage

import torch
from ast_torch.model import ASTransformer

# Create dummy data
x = torch.randn(2, 16)

# Initialize model
model = ASTransformer(
    dim=4, seqlen=16, dim_head=4, heads=4, depth=2, patch_size=4
)

# Run model and print output shape
print(model(x).shape)

Citation

@misc{gong2021ast,
    title={AST: Audio Spectrogram Transformer}, 
    author={Yuan Gong and Yu-An Chung and James Glass},
    year={2021},
    eprint={2104.01778},
    archivePrefix={arXiv},
    primaryClass={cs.SD}
}

License

MIT

Metadata

Release files for ast-torch 0.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ast-torch 0.0.5
File	Size	Uploaded
ast_torch-0.0.5.tar.gz	6.9 kB	Jan 1, 2024	Details

Built distribution (wheel)

Table of built distributions (wheels) for ast-torch 0.0.5
File	Interpreter	ABI	Platform	Reset
ast_torch-0.0.5-py3-none-any.whl 7.2 kB Jan 1, 2024	Python 3	none	any	Details

Total release size: 14.1 kB

Release files / ast_torch-0.0.5.tar.gz

Download URL	ast_torch-0.0.5.tar.gz
Size	6.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`2db6f9d1c9b9f732881a1328905e084ef6073b7fda858d4aa12bb79a6d86582c`
BLAKE2b-256 checksum How to use checksums	`89495c19a9ad444f07eea9d7f4e051a24ff0364e4151431f1b151e596c98b189`
Upload date	Jan 1, 2024
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0`

Release files / ast_torch-0.0.5-py3-none-any.whl

Download URL	ast_torch-0.0.5-py3-none-any.whl
Size	7.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`1920586c09473c403878e20c3e483194d0d8f4137ea644d8d9a24ae49bc36e55`
BLAKE2b-256 checksum How to use checksums	`5ea1c942462042444954e43c5476d5868289268ef9b8993b31e40c5233b5a7ed`
Upload date	Jan 1, 2024
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0`