Upload 5 files

.gitignore

@@ -0,0 +1,6 @@
+.cog
+__pycache__
+.DS_Store
+*.wav
+*.mp4
+*.png

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 fofrAI
+
+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

@@ -1,10 +1,2 @@
----
-title: Cog
-emoji: 👀
-colorFrom: pink
-colorTo: indigo
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# audio-to-waveform
+Convert an audio file to a waveform video

cog.yaml

@@ -0,0 +1,12 @@
+# Configuration for Cog ⚙️
+# Reference: https://github.com/replicate/cog/blob/main/docs/yaml.md
+
+build:
+  gpu: false
+  python_version: "3.9"
+  system_packages:
+    - "ffmpeg"
+    - "imagemagick"
+  python_packages:
+    - "gradio==3.50.2"
+predict: "predict.py:Predictor"

predict.py

@@ -0,0 +1,53 @@
+import subprocess
+from cog import BasePredictor, Input, Path
+import gradio as gr
+import tempfile
+
+class Predictor(BasePredictor):
+    def predict(self,
+        audio: Path = Input(description="Audio file to create waveform from"),
+        bg_color: str = Input(description="Background color of waveform", default="#000000"),
+        fg_alpha: float = Input(description="Opacity of foreground waveform", default=0.75),
+        bars_color: str = Input(description="Color of waveform bars", default="#ffffff"),
+        bar_count: int = Input(description="Number of bars in waveform", default=100),
+        bar_width: float = Input(description="Width of bars in waveform. 1 represents full width, 0.5 represents half width, etc.", default=0.4),
+        caption_text: str = Input(description="Caption text for the video", default=""),
+    ) -> Path:
+        """Make waveform video from audio file"""
+        waveform_video = gr.make_waveform(
+            str(audio),
+            bg_color=bg_color,
+            fg_alpha=fg_alpha,
+            bars_color=bars_color,
+            bar_count=bar_count,
+            bar_width=bar_width,
+        )
+
+        if caption_text == "" or caption_text is None:
+            return Path(waveform_video)
+        else:
+            padded_waveform_path = tempfile.mktemp(suffix=".mp4")
+            background_image_path = tempfile.mktemp(suffix=".png")
+            final_video_path = tempfile.mktemp(suffix=".mp4")
+
+            # Add padding to the top of the waveform video
+            subprocess.run([
+                'ffmpeg', '-y', '-i', waveform_video, '-vf',
+                f'pad=width=1000:height=667:x=0:y=467:color={bg_color[1:]}',
+                padded_waveform_path
+            ], check=True)
+
+            # Create an image using ImageMagick
+            subprocess.run([
+                'convert', '-background', bg_color, '-fill', bars_color, '-font', 'font/Roboto-Black.ttf',
+                '-pointsize', '48', '-size', '900x367', '-gravity', 'center', f'caption:{caption_text}',
+                '-bordercolor', bg_color, '-border', '40', background_image_path
+            ], check=True)
+
+            # Overlay the image on the padded waveform video
+            subprocess.run([
+                'ffmpeg', '-y', '-i', padded_waveform_path, '-i', background_image_path,
+                '-filter_complex', 'overlay=0:0', final_video_path
+            ], check=True)
+
+        return Path(final_video_path)