Duplicate from Kevin676/Speechbrain-Speech-enhancement

Co-authored-by: Kevin Wang <[email protected]>

.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 Enhancement
+emoji: 👁
+colorFrom: gray
+colorTo: pink
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: Kevin676/Speechbrain-Speech-enhancement
+---
+
+# 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 +1,28 @@
+import torch
+import torchaudio
+from speechbrain.pretrained import SpectralMaskEnhancement
+import gradio as gr
+
+enhance_model = SpectralMaskEnhancement.from_hparams(
+    source="speechbrain/metricgan-plus-voicebank",
+    savedir="pretrained_models/metricgan-plus-voicebank",
+)
+
+def speechbrain(aud):
+  # Load and add fake batch dimension
+  noisy = enhance_model.load_audio(
+      aud
+  ).unsqueeze(0)
+  enhanced = enhance_model.enhance_batch(noisy, lengths=torch.tensor([1.]))
+  torchaudio.save('enhanced.wav', enhanced.cpu(), 16000)
+  return 'enhanced.wav'
+  
+inputs = gr.Audio(label="Input Audio", type="filepath")
+outputs = gr.Audio(label="Output Audio", type="filepath")
+title = "Speechbrain Speech Enhancement"
+description = "Gradio demo for Speech enhancement with 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/2104.03538' target='_blank'>MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement</a> | <a href='https://github.com/speechbrain/speechbrain' target='_blank'>Github Repo</a></p>"
+examples = [
+    ['samples_audio_samples_example_fr.wav']
+]
+gr.Interface(speechbrain, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()

requirements.txt

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