add cell to generate audios

notebooks/test-model.ipynb

@@ -72,14 +72,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "b809fed5",
+   "execution_count": null,
+   "id": "e0f6e8fd",
    "metadata": {},
    "outputs": [],
    "source": [
     "model_id = \"teticio/audio-diffusion-256\"\n",
     "ddpm = DDPMPipeline.from_pretrained(model_id)  # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference\n",
-    "ddpm.to(\"cuda\")\n",
+    "ddpm.to(\"cuda\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b809fed5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "images = ddpm(output_type=\"numpy\")[\"sample\"]\n",
     "images = (images * 255).round().astype(\"uint8\").transpose(0, 3, 1, 2)"
    ]
@@ -145,6 +154,29 @@
     "Audio(data=audio, rate=mel.get_sample_rate())"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "ba4ccac5",
+   "metadata": {},
+   "source": [
+    "### Generate audios"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "300a6a8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "while True:\n",
+    "    images = ddpm(output_type=\"numpy\")[\"sample\"]\n",
+    "    images = (images * 255).round().astype(\"uint8\").transpose(0, 3, 1, 2)\n",
+    "    image = Image.fromarray(images[0][0])\n",
+    "    audio = mel.image_to_audio(image)\n",
+    "    display(Audio(data=audio, rate=mel.get_sample_rate()))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "ef54cef3",