add notebook for gradio app

README.md

@@ -9,7 +9,7 @@ app_file: app.py
 pinned: false
 license: gpl-3.0
 ---
-# audio-diffusion [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/teticio/audio-diffusion/blob/master/notebooks/test_model.ipynb)
+# audio-diffusion [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/teticio/audio-diffusion/blob/master/notebooks/gradio_app.ipynb)
 
 ### Apply [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) using the new Hugging Face [diffusers](https://github.com/huggingface/diffusers) package to synthesize music instead of images.
 

app.py

@@ -15,30 +15,31 @@ def generate_spectrogram_audio_and_loop(model_id):
     return image, (sample_rate, audio), (sample_rate, loop)
 
 
+demo = gr.Interface(fn=generate_spectrogram_audio_and_loop,
+                    title="Audio Diffusion",
+                    description="Generate audio using Huggingface diffusers.\
+        This takes about 20 minutes without a GPU, so why not make yourself a \
+            cup of tea in the meantime?",
+                    inputs=[
+                        gr.Dropdown(label="Model",
+                                    choices=[
+                                        "teticio/audio-diffusion-256",
+                                        "teticio/audio-diffusion-breaks-256"
+                                    ],
+                                    value="teticio/audio-diffusion-256")
+                    ],
+                    outputs=[
+                        gr.Image(label="Mel spectrogram", image_mode="L"),
+                        gr.Audio(label="Audio"),
+                        gr.Audio(label="Loop"),
+                    ],
+                    allow_flagging="never")
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--port", type=int)
     parser.add_argument("--server", type=int)
     args = parser.parse_args()
-
-    demo = gr.Interface(
-        fn=generate_spectrogram_audio_and_loop,
-        title="Audio Diffusion",
-        description="Generate audio using Huggingface diffusers.\
-            This takes about 20 minutes without a GPU, so why not make yourself a cup of tea in the meantime?",
-        inputs=[
-            gr.Dropdown(label="Model",
-                        choices=[
-                            "teticio/audio-diffusion-256",
-                            "teticio/audio-diffusion-breaks-256"
-                        ],
-                        value="teticio/audio-diffusion-256")
-        ],
-        outputs=[
-            gr.Image(label="Mel spectrogram", image_mode="L"),
-            gr.Audio(label="Audio"),
-            gr.Audio(label="Loop"),
-        ],
-        allow_flagging="never"
-    )
     demo.launch(server_name=args.server or "0.0.0.0", server_port=args.port)
+else:
+    demo.launch(share=True)

notebooks/gradio_app.ipynb

@@ -0,0 +1,123 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a489aa44",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/teticio/audio-diffusion/blob/master/notebooks/gradio_app.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9502ffa7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    # are we running on Google Colab?\n",
+    "    import google.colab\n",
+    "    !git clone -q https://github.com/teticio/audio-diffusion.git\n",
+    "    %cd audio-diffusion\n",
+    "    !pip install -q -r requirements.txt\n",
+    "except:\n",
+    "    pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8f8b6e43",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import sys\n",
+    "sys.path.insert(0, os.path.dirname(os.path.abspath(\"\")))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2d948967",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7861/\n",
+      "Running on public URL: https://24053.gradio.app\n",
+      "\n",
+      "This share link expires in 72 hours. For free permanent hosting, check out Spaces: https://huggingface.co/spaces\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"https://24053.gradio.app\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import app"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "46f03607",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "huggingface",
+   "language": "python",
+   "name": "huggingface"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/test_model.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "0a627a6f",
+   "id": "62c5865f",
    "metadata": {},
    "source": [
     "<a href=\"https://colab.research.google.com/github/teticio/audio-diffusion/blob/master/notebooks/test_model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"

streamlit_app.py

@@ -9,8 +9,8 @@ from audiodiffusion import AudioDiffusion
 if __name__ == "__main__":
     st.header("Audio Diffusion")
     st.markdown("Generate audio using Huggingface diffusers.\
-        This takes about 20 minutes without a GPU, so why not make yourself a cup of tea in the meantime?"
-                )
+        This takes about 20 minutes without a GPU, so why not make yourself a \
+            cup of tea in the meantime?")
 
     model_id = st.selectbox(
         "Model",