https://github.com/yoyololicon/audiotensor

https://github.com/yoyololicon/audiotensor

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/yoyololicon/audiotensor
• Owner: yoyololicon
• Created: 2024-01-31T14:52:22.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-04-25T07:47:50.000Z (7 months ago)
• Last Synced: 2024-05-01T18:53:11.694Z (7 months ago)
• Language: Python
• Size: 9.77 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# AudioTensor

- Wrap your tensor as `AudioTensor(tensor, hop_length)` and use it as a regular tensor.

- For `ndim > 1`, the shape is `(B, T, ...)`, where `B` is the batch size and `T` is the number of frames.

- For `ndim == 1`, the shape is `(B,)` and `hop_length = -1`.

- Tensors with different `hop_length` will be automatically linearly resampled to the maximum common divisor of `hop_length`s when performing operations.

- `set_hop_length(hop_length)` will resample the tensor to the new `hop_length`.

- `reduce_hop_length()` will upsample the tensor to `hop_length = 1`.

- `steps` will return the size of `T` in the tensor.

- `truncate(steps)` will truncate the tensor to the given `steps`.

- `unfold(size, step)` return a view of the tensor with a sliding window of size `size` and step `step` along the `T` dimension.