Update README.md

README.md

@@ -17,15 +17,12 @@ metrics:
 ---
 
 
-# SepFormer trained on WSJ0-2Mix
+# SI-SNR Estimator
 
-This repository provides all the necessary tools to perform audio source separation with a [SepFormer](https://arxiv.org/abs/2010.13154v2) 
-model, implemented with SpeechBrain, and pretrained on WSJ0-2Mix dataset. For a better experience we encourage you to learn more about
-[SpeechBrain](https://speechbrain.github.io). The model performance is 22.4 dB on the test set of WSJ0-2Mix dataset.
+This repository provides all the necessary tools to perform blind SI-SNR estimation from mixture signal + estimated sources. 
+The SI-SNR estimator is trained with a recordings from the WHAMR! and LibriMix datasets. We used a mixture of 9 separators to create the training data on the fly. 
 
-| Release | Test-Set SI-SNRi | Test-Set SDRi |
-|:-------------:|:--------------:|:--------------:|
-| 09-03-21 | 22.4dB | 22.6dB |
+This model is released together with the REAL-M dataset for source separation on in-the-wild speech mixtures. 
 
 
 ## Install SpeechBrain
@@ -39,20 +36,6 @@ pip install speechbrain
 Please notice that we encourage you to read our tutorials and learn more about
 [SpeechBrain](https://speechbrain.github.io).
 
-### Perform source separation on your own audio file
-```python
-from speechbrain.pretrained import SepformerSeparation as separator
-import torchaudio
-
-model = separator.from_hparams(source="speechbrain/sepformer-wsj02mix", savedir='pretrained_models/sepformer-wsj02mix')
-
-# for custom file, change path
-est_sources = model.separate_file(path='speechbrain/sepformer-wsj02mix/test_mixture.wav') 
-
-torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
-torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)
-
-```
 
 ### Inference on GPU
 To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.