Audio-to-Audio
speechbrain
English
Source Separation
Speech Separation
Audio Source Separation
WSJ02Mix
SepFormer
Transformer
audio-source-separation
Instructions to use admin-spsoft/Speechbrain_SPSoft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use admin-spsoft/Speechbrain_SPSoft with speechbrain:
from speechbrain.pretrained import SepformerSeparation model = SepformerSeparation.from_hparams( "admin-spsoft/Speechbrain_SPSoft" ) model.separate_file("file.wav") - Notebooks
- Google Colab
- Kaggle
Set custom endpoint handler sample rate to 16 kHz
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -15,7 +15,7 @@ if not hasattr(torchaudio, "list_audio_backends"):
|
|
| 15 |
from speechbrain.inference.separation import SepformerSeparation
|
| 16 |
|
| 17 |
|
| 18 |
-
TARGET_SAMPLE_RATE =
|
| 19 |
|
| 20 |
|
| 21 |
class EndpointHandler:
|
|
|
|
| 15 |
from speechbrain.inference.separation import SepformerSeparation
|
| 16 |
|
| 17 |
|
| 18 |
+
TARGET_SAMPLE_RATE = 16000
|
| 19 |
|
| 20 |
|
| 21 |
class EndpointHandler:
|