Downloads · 30 days
0
TDANetBest-2ms-LRS2
JusperLee/TDANetBest-2ms-LRS2
TDANetBest-2ms-LRS2 is a audio-to-audio model from JusperLee. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
[](https://paperswithcode.com/sota/speech-separation-on-libri2mix?p=an-efficient-encoder-decoder-architecture) [](https://paperswithcode.com/sota/speech-separation-on-wham?p=an-efficient-encoder-decoder-architecture)
Access
Public
Updated Oct 12, 2023
Repo size
29.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin29.9 MB · 100%
At a glance
- Task
- Audio-to-Audio
- License
- apache-2.0
- Access
- Public
- Created
- Oct 12, 2023
- Updated
- Oct 12, 2023
- SHA
- 4fc54289
Model card
From the Hugging Face model README
An efficient encoder-decoder architecture with top-down attention for speech separation
This repository is the official implementation of An efficient encoder-decoder architecture with top-down attention for speech separation Paper link.
@inproceedings{tdanet2023iclr,
title={An efficient encoder-decoder architecture with top-down attention for speech separation},
author={Li, Kai and Yang, Runxuan and Hu, Xiaolin},
booktitle={ICLR},
year={2023}
}
Training Dataset
- LRS2-2Mix
Config
enc_kernel_size: 2
in_channels: 512
num_blocks: 16
num_sources: 2
out_channels: 128
upsampling_depth: 5
- Task
- Audio-to-Audio
- License
- apache-2.0
- Languages
- en
- Created
- Oct 12, 2023
- Updated
- Oct 12, 2023