-
Notifications
You must be signed in to change notification settings - Fork 21
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
86 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| # 🤗 Speech Enhancement Checkpoints | ||
|
|
||
| Welcome to the Checkpoints folder! Here you will find instructions on how to download and set up pre-trained speech enhancement models for testing. | ||
|
|
||
| ## Instructions | ||
|
|
||
| 1. **Download Pre-trained Models**: | ||
| - Visit the [GitHub Release page](https://github.com/JusperLee/LibriSpace/releases) of the LibriSpace repository. | ||
| - Download the desired pre-trained model files. Each model is available as a zip file named according to the following list: | ||
|
|
||
| 2. **Extract the Models**: | ||
| - Extract the downloaded zip files into this `LibriSpace/enh-checkpoints` folder. Each zip file contains the pre-trained model weights and necessary files for model testing. | ||
|
|
||
| 3. **Test the Models**: | ||
| - Once extracted, you can use the models for testing purposes with your speech enhancement tasks. Ensure that your testing scripts point to the correct model paths. | ||
|
|
||
| ## Model List | ||
|
|
||
| | File Name | Link | | ||
| |-------------------------------|---------------------------------------------------------------------------| | ||
| | DCCRN-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/DCCRN-Music.zip) | | ||
| | DCCRN-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/DCCRN-Noise.zip) | | ||
| | FastFullband-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/FastFullband-Music.zip) | | ||
| | FastFullband-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/FastFullband-Noise.zip) | | ||
| | Fullband-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/Fullband-Music.zip) | | ||
| | Fullband-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/Fullband-Noise.zip) | | ||
| | FullSubNet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/FullSubNet-Music.zip) | | ||
| | FullSubNet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/FullSubNet-Noise.zip) | | ||
| | FullSubNet-Plus-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/FullSubNet-Plus-Music.zip) | | ||
| | FullSubNet-Plus-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/FullSubNet-Plus-Noise.zip) | | ||
| | G2Net-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/G2Net-Music.zip) | | ||
| | G2Net-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/G2Net-Noise.zip) | | ||
| | GaGNet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/GaGNet-Music.zip) | | ||
| | GaGNet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/GaGNet-Noise.zip) | | ||
| | InterSubNet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/InterSubNet-Music.zip) | | ||
| | InterSubNet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/InterSubNet-Noise.zip) | | ||
| | SUDORMRF-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/SUDORMRF-Music.zip) | | ||
| | SUDORMRF-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/SUDORMRF-Noise.zip) | | ||
| | TaylorSENet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/TaylorSENet-Music.zip) | | ||
| | TaylorSENet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Enh/TaylorSENet-Noise.zip) | | ||
|
|
||
| Download these model zip files from [LibriSpace GitHub Releases](https://github.com/JusperLee/LibriSpace/releases) and extract them here to start using the pre-trained models for your speech enhancement applications. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| # 🤗 Speech Separation Checkpoints | ||
|
|
||
| Welcome to the Checkpoints folder! Here you will find instructions on how to download and set up pre-trained speech separation models for testing. | ||
|
|
||
| ## Instructions | ||
|
|
||
| 1. **Download Pre-trained Models**: | ||
| - Visit the [GitHub Release page](https://github.com/JusperLee/LibriSpace/releases) of the LibriSpace repository. | ||
| - Download the desired pre-trained model files. Each model is available as a zip file named according to the following list: | ||
|
|
||
| 2. **Extract the Models**: | ||
| - Extract the downloaded zip files into this `LibriSpace/sep-checkpoints` folder. Each zip file contains the pre-trained model weights and necessary files for model testing. | ||
|
|
||
| 3. **Test the Models**: | ||
| - Once extracted, you can use the models for testing purposes with your speech separation tasks. Ensure that your testing scripts point to the correct model paths. | ||
|
|
||
| ## Model List | ||
|
|
||
| | File Name | Link | | ||
| |-------------------------------|---------------------------------------------------------------------------| | ||
| | AFRCNN-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/AFRCNN-Music.zip) | | ||
| | AFRCNN-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/AFRCNN-Noise.zip) | | ||
| | BSRNN-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/BSRNN-Music.zip) | | ||
| | BSRNN-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/BSRNN-Noise.zip) | | ||
| | DPRNN-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/DPRNN-Music.zip) | | ||
| | DPRNN-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/DPRNN-Noise.zip) | | ||
| | DPTNet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/DPTNet-Music.zip) | | ||
| | DPTNet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/DPTNet-Noise.zip) | | ||
| | Mossformer2-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/Mossformer2-Music.zip) | | ||
| | Mossformer2-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/Mossformer2-Noise.zip) | | ||
| | Mossformer-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/Mossformer-Music.zip) | | ||
| | Mossformer-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/Mossformer-Noise.zip) | | ||
| | Skim-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/Skim-Music.zip) | | ||
| | Skim-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/Skim-Noise.zip) | | ||
| | SuDORMRF-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/SuDORMRF-Music.zip) | | ||
| | SUDORMRF-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/SUDORMRF-Noise.zip) | | ||
| | TDANet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/TDANet-Music.zip) | | ||
| | TDANet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/TDANet-Noise.zip) | | ||
| | TFGNet-Music | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/TFGNet-Music.zip) | | ||
| | TFGNet-Noise | [checkpoint](https://github.com/JusperLee/LibriSpace/releases/download/Sep/TFGNet-Noise.zip) | | ||
|
|
||
| Download these model zip files from [LibriSpace GitHub Releases](https://github.com/JusperLee/LibriSpace/releases) and extract them here to start using the pre-trained models for your speech separation applications. |