Shokoufehhh commited on
Commit
e59dff9
·
verified ·
1 Parent(s): 67a2b1f

Delete config.yaml

Browse files
Files changed (1) hide show
  1. config.yaml +0 -58
config.yaml DELETED
@@ -1,58 +0,0 @@
1
- # General model information
2
- language: en
3
- tags:
4
- - speech-enhancement
5
- - dereverberation
6
- - diffusion-models
7
- - generative-models
8
- - pytorch
9
- - audio-processing
10
- license: mit
11
- datasets:
12
- - VoiceBank-DEMAND
13
- - WSJ0-CHiME3
14
- - WSJ0-REVERB
15
- - EARS-WHAM
16
- - EARS-Reverb
17
- model_name: speech-enhancement-dereverberation-diffusion
18
- model_type: diffusion-based-generative-model
19
- library_name: pytorch
20
- pipeline_tag: audio-to-audio
21
-
22
- # Important files for the model
23
- key_files:
24
- - model.py
25
- - train.py
26
- - inference.py
27
- - enhancement.py
28
- - requirements.txt
29
- - calc_metrics.py
30
-
31
- # Pretrained model checkpoints
32
- pretrained_checkpoints:
33
- voicebank_demand:
34
- description: SGMSE+ trained on VoiceBank-DEMAND
35
- download_link: https://drive.google.com/drive/folders/1CSnkhUSoiv3RG0xg7WEcVapyLuwDaLbe?usp=sharing
36
- gdown_id: 1_H3EXvhcYBhOZ9QNUcD5VZHc6ktrRbwQ
37
- wsj0_chime3:
38
- description: SGMSE+ trained on WSJ0-CHiME3
39
- download_link: https://drive.google.com/drive/folders/1CSnkhUSoiv3RG0xg7WEcVapyLuwDaLbe?usp=sharing
40
- gdown_id: 16K4DUdpmLhDNC7pJhBBc08pkSIn_yMPi
41
- wsj0_reverb:
42
- description: SGMSE+ trained on WSJ0-REVERB
43
- download_link: https://drive.google.com/drive/folders/1082_PSEgrqoVVrNsAkSIcpLF1AAtzGwV?usp=sharing
44
- gdown_id: 1eiOy0VjHh9V9ZUFTxu1Pq2w19izl9ejD
45
- ears_wham:
46
- description: SGMSE+ trained on EARS-WHAM
47
- download_link: https://drive.google.com/drive/folders/1Tn6pVwjxUAy1DJ8167JCg3enuSi0hiw5?usp=sharing
48
- gdown_id: 1t_DLLk8iPH6nj8M5wGeOP3jFPaz3i7K5
49
- ears_reverb:
50
- description: SGMSE+ trained on EARS-Reverb
51
- download_link: https://drive.google.com/drive/folders/1PunXuLbuyGkknQCn_y-RCV2dTZBhyE3V?usp=sharing
52
- gdown_id: 1PunXuLbuyGkknQCn_y-RCV2dTZBhyE3V
53
-
54
- # Citation references for the model
55
- citations:
56
- - '@inproceedings{welker22speech, author={Simon Welker and Julius Richter and Timo Gerkmann}, title={Speech Enhancement with Score-Based Generative Models in the Complex {STFT} Domain}, year={2022}, booktitle={Proc. Interspeech 2022}, pages={2928--2932}, doi={10.21437/Interspeech.2022-10653}}'
57
- - '@article{richter2023speech, title={Speech Enhancement and Dereverberation with Diffusion-based Generative Models}, author={Richter, Julius and Welker, Simon and Lemercier, Jean-Marie and Lay, Bunlong and Gerkmann, Timo}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, volume={31}, pages={2351-2364}, year={2023}, doi={10.1109/TASLP.2023.3285241}}'
58
- - '@inproceedings{richter2024ears, title={{EARS}: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation}, author={Richter, Julius and Wu, Yi-Chiao and Krenn, Steven and Welker, Simon and Lay, Bunlong and Watanabe, Shinjii and Richard, Alexander and Gerkmann, Timo}, booktitle={ISCA Interspeech}, year={2024}}'