save notebook output

save_model.ipynb

@@ -161,17 +161,10 @@
    "metadata": {},
    "outputs": [
     {
-     "ename": "RuntimeError",
-     "evalue": "The size of tensor a (1600) must match the size of tensor b (1592) at non-singleton dimension 2",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[3], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# decoding (from zq -- discrete latent vectors)\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m waveform \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mzq\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mzq\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mwaveform.shape:\u001b[39m\u001b[38;5;124m'\u001b[39m, waveform\u001b[38;5;241m.\u001b[39mshape)\n",
-      "File \u001b[1;32mc:\\Users\\dslee\\anaconda3\\envs\\sound_effect_variation_generation\\lib\\site-packages\\torch\\utils\\_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[0;32m    114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m    115\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[1;32m--> 116\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32m~\\.cache\\huggingface\\modules\\transformers_modules\\hance-ai\\descript-audio-codec-16khz\\67523817a195ced323d12ce4c439590547d8e9c7\\model.py:159\u001b[0m, in \u001b[0;36mDAC.decode\u001b[1;34m(self, zq, s)\u001b[0m\n\u001b[0;32m    156\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39meval()\n\u001b[0;32m    158\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(zq,\u001b[38;5;28mtype\u001b[39m(\u001b[38;5;28;01mNone\u001b[39;00m)):\n\u001b[1;32m--> 159\u001b[0m     waveform \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_chunk_decoding\u001b[49m\u001b[43m(\u001b[49m\u001b[43mzq\u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# (b, 1, length); output always has a mono-channel.\u001b[39;00m\n\u001b[0;32m    160\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(s,\u001b[38;5;28mtype\u001b[39m(\u001b[38;5;28;01mNone\u001b[39;00m)):\n\u001b[0;32m    161\u001b[0m     zq \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcode_to_zq(s)\n",
-      "File \u001b[1;32m~\\.cache\\huggingface\\modules\\transformers_modules\\hance-ai\\descript-audio-codec-16khz\\67523817a195ced323d12ce4c439590547d8e9c7\\model.py:189\u001b[0m, in \u001b[0;36mDAC._chunk_decoding\u001b[1;34m(self, zq)\u001b[0m\n\u001b[0;32m    187\u001b[0m     overlap_x_from_prev_x \u001b[38;5;241m=\u001b[39m waveform_concat[:,:,\u001b[38;5;241m-\u001b[39moverlap_size_in_data_space:]  \u001b[38;5;66;03m# (b, 1, overlap_size_in_data_space)\u001b[39;00m\n\u001b[0;32m    188\u001b[0m     overlap_x_from_new_x \u001b[38;5;241m=\u001b[39m waveform[:,:,:overlap_size_in_data_space]  \u001b[38;5;66;03m# (b, 1, overlap_size_in_data_space)\u001b[39;00m\n\u001b[1;32m--> 189\u001b[0m     overlap \u001b[38;5;241m=\u001b[39m (\u001b[43moverlap_x_from_prev_x\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43moverlap_x_from_new_x\u001b[49m) \u001b[38;5;241m/\u001b[39m \u001b[38;5;241m2\u001b[39m  \u001b[38;5;66;03m# take mean; maybe there's a better strategy but it seems to work fine.\u001b[39;00m\n\u001b[0;32m    190\u001b[0m     waveform_concat \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mcat((prev_x, overlap, rest_of_new_x), dim\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)  \u001b[38;5;66;03m# (b, 1, ..)\u001b[39;00m\n\u001b[0;32m    191\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
-      "\u001b[1;31mRuntimeError\u001b[0m: The size of tensor a (1600) must match the size of tensor b (1592) at non-singleton dimension 2"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "waveform.shape: torch.Size([1, 1, 159912])\n"
      ]
     }
    ],