Audio-to-Audio
speechbrain
English
Source Separation
Speech Separation
Audio Source Separation
WSJ02Mix
SepFormer
Transformer
audio-source-separation
Instructions to use speechbrain/sepformer-wsj02mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use speechbrain/sepformer-wsj02mix with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "speechbrain/sepformer-wsj02mix" ) model.separate_file("file.wav") - Notebooks
- Google Colab
- Kaggle
Commit ·
378e4ce
1
Parent(s): 6ac2d26
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ model, implemented with SpeechBrain, and pretrained on WSJ0-2Mix dataset. For a
|
|
| 24 |
|
| 25 |
| Release | Test-Set SI-SNR | Test-Set SDR |
|
| 26 |
|:-------------:|:--------------:|:--------------:|
|
| 27 |
-
| 09-03-21 | 22.
|
| 28 |
|
| 29 |
|
| 30 |
## Install SpeechBrain
|
|
|
|
| 24 |
|
| 25 |
| Release | Test-Set SI-SNR | Test-Set SDR |
|
| 26 |
|:-------------:|:--------------:|:--------------:|
|
| 27 |
+
| 09-03-21 | 22.5dB | 22.7dB |
|
| 28 |
|
| 29 |
|
| 30 |
## Install SpeechBrain
|