Init

.gitignore

@@ -0,0 +1,9 @@
+/data
+/runs
+/scripts
+/dist
+/build
+/*.egg-info
+/flagged
+version.py
+__pycache__

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Resemble AI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,15 @@
+---
+title: Resemble Enhance
+emoji: 🚀
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 4.8.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# Resemble Enhance
+
+Resemble Enhance is an AI-powered tool that aims to improve the overall quality of speech by performing denoising and enhancement. It consists of two modules: a denoiser, which separates speech from a noisy audio, and an enhancer, which further boosts the perceptual audio quality by restoring audio distortions and extending the audio bandwidth. The two models are trained on high-quality 44.1kHz speech data that guarantees the enhancement of your speech with high quality.

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import torch
+import torchaudio
+
+from resemble_enhance.enhancer.inference import denoise, enhance
+
+if torch.cuda.is_available():
+    device = "cuda"
+else:
+    device = "cpu"
+
+
+def _fn(path, solver, nfe, tau, denoising):
+    if path is None:
+        return None, None
+
+    solver = solver.lower()
+    nfe = int(nfe)
+    lambd = 0.9 if denoising else 0.1
+
+    dwav, sr = torchaudio.load(path)
+    dwav = dwav.mean(dim=0)
+
+    wav1, new_sr = denoise(dwav, sr, device)
+    wav2, new_sr = enhance(dwav, sr, device, nfe=nfe, solver=solver, lambd=lambd, tau=tau)
+
+    wav1 = wav1.cpu().numpy()
+    wav2 = wav2.cpu().numpy()
+
+    return (new_sr, wav1), (new_sr, wav2)
+
+
+def main():
+    inputs: list = [
+        gr.Audio(type="filepath", label="Input Audio"),
+        gr.Dropdown(choices=["Midpoint", "RK4", "Euler"], value="Midpoint", label="CFM ODE Solver"),
+        gr.Slider(minimum=1, maximum=128, value=64, step=1, label="CFM Number of Function Evaluations"),
+        gr.Slider(minimum=0, maximum=1, value=0.5, step=0.01, label="CFM Prior Temperature"),
+        gr.Checkbox(value=False, label="Denoise Before Enhancement"),
+    ]
+
+    outputs: list = [
+        gr.Audio(label="Output Denoised Audio"),
+        gr.Audio(label="Output Enhanced Audio"),
+    ]
+
+    interface = gr.Interface(
+        fn=_fn,
+        title="Resemble Enhance",
+        description="AI-driven audio enhancement for your audio files, powered by Resemble AI.",
+        inputs=inputs,
+        outputs=outputs,
+    )
+
+    interface.launch()
+
+
+if __name__ == "__main__":
+    main()

packages.txt

@@ -0,0 +1 @@
+libsox-dev

pyproject.toml

@@ -0,0 +1,6 @@
+[tool.black]
+line-length = 120
+target-version = ['py310']
+
+[tool.isort]
+line_length = 120

requirements.txt

@@ -0,0 +1 @@
+resemble-enhance