Duplicate from akhaliq/speechbrain-speech-seperation

Co-authored-by: AK <akhaliq@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+title: Speechbrain-speech-seperation
+emoji: 👁
+colorFrom: red
+colorTo: gray
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: akhaliq/speechbrain-speech-seperation
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,25 @@
+from speechbrain.pretrained import SepformerSeparation as separator
+import torchaudio
+import gradio as gr
+
+model = separator.from_hparams(source="speechbrain/sepformer-wsj02mix", savedir='pretrained_models/sepformer-wsj02mix')
+
+def speechbrain(aud):
+  est_sources = model.separate_file(path=aud.name) 
+  torchaudio.save("source1hat.wav", est_sources[:, :, 0].detach().cpu(), 8000)
+  torchaudio.save("source2hat.wav", est_sources[:, :, 1].detach().cpu(), 8000)
+  return "source1hat.wav", "source2hat.wav"
+
+inputs = gr.inputs.Audio(label="Input Audio", type="file")
+outputs =  [
+  gr.outputs.Audio(label="Output Audio One", type="file"),
+  gr.outputs.Audio(label="Output Audio Two", type="file")
+]
+
+title = "Speech Seperation"
+description = "Gradio demo for Speech Seperation by SpeechBrain. To use it, simply upload your audio, or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2010.13154' target='_blank'>Attention is All You Need in Speech Separation</a> | <a href='https://github.com/speechbrain/speechbrain/tree/develop/recipes/WSJ0Mix/separation' '_blank'>Github Repo</a></p>"
+examples = [
+    ['samples_audio_samples_test_mixture.wav']
+]
+gr.Interface(speechbrain, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()

requirements.txt

@@ -0,0 +1,2 @@
+speechbrain
+torchaudio