tidy

notebooks/test_model.ipynb

@@ -60,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "mel = Mel(x_res=256, y_res=256)\n",
+    "mel = Mel()\n",
     "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
     "generator = torch.Generator(device=device)"
    ]
@@ -420,7 +420,7 @@
    "outputs": [],
    "source": [
     "image = ds['train'][264]['image']\n",
-    "display(Audio(mel.image_to_audio(image), rate=mel.get_sample_rate()))"
+    "display(Audio(mel.image_to_audio(image), rate=sample_rate))"
    ]
   },
   {
@@ -462,7 +462,7 @@
    "outputs": [],
    "source": [
     "image2 = ds['train'][15978]['image']\n",
-    "display(Audio(mel.image_to_audio(image2), rate=mel.get_sample_rate()))"
+    "display(Audio(mel.image_to_audio(image2), rate=sample_rate))"
    ]
   },
   {
@@ -486,8 +486,8 @@
     "_, (sample_rate, audio) = audio_diffusion.generate_spectrogram_and_audio(\n",
     "    noise=audio_diffusion.pipe.slerp(noise, noise2, alpha),\n",
     "    generator=generator)\n",
-    "display(Audio(mel.image_to_audio(image), rate=mel.get_sample_rate()))\n",
-    "display(Audio(mel.image_to_audio(image2), rate=mel.get_sample_rate()))\n",
+    "display(Audio(mel.image_to_audio(image), rate=sample_rate))\n",
+    "display(Audio(mel.image_to_audio(image2), rate=sample_rate))\n",
     "display(Audio(audio, rate=sample_rate))"
    ]
   },
@@ -600,8 +600,8 @@
     "_, (sample_rate, audio3) = audio_diffusion.generate_spectrogram_and_audio(\n",
     "    noise=audio_diffusion.pipe.slerp(latents, latents2, alpha),\n",
     "    generator=generator)\n",
-    "display(Audio(audio, rate=mel.get_sample_rate()))\n",
-    "display(Audio(audio2, rate=mel.get_sample_rate()))\n",
+    "display(Audio(audio, rate=sample_rate))\n",
+    "display(Audio(audio2, rate=sample_rate))\n",
     "display(Audio(audio3, rate=sample_rate))"
    ]
   },