clarification

notebooks/test_model.ipynb

@@ -492,7 +492,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5b7081f7",
+   "id": "9b244547",
    "metadata": {},
    "source": [
     "## Latent Audio Diffusion\n",
@@ -502,7 +502,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "17610772",
+   "id": "a88b3fbb",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -512,7 +512,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9e6c73e6",
+   "id": "15e353ee",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -522,7 +522,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d37a03a9",
+   "id": "fa0f0c8c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -537,7 +537,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c0328a56",
+   "id": "73dc575d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -551,7 +551,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bd1f2b58",
+   "id": "428d2d67",
    "metadata": {},
    "source": [
     "### Interpolation in latent space\n",
@@ -561,43 +561,43 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "23ff0ee7",
+   "id": "72211c2b",
    "metadata": {},
    "outputs": [],
    "source": [
     "generator.manual_seed(seed)\n",
-    "noise = torch.randn((1, audio_diffusion.pipe.unet.in_channels,\n",
+    "latents = torch.randn((1, audio_diffusion.pipe.unet.in_channels,\n",
     "                     audio_diffusion.pipe.unet.sample_size[0],\n",
     "                     audio_diffusion.pipe.unet.sample_size[1]),\n",
     "                    generator=generator)\n",
-    "noise.shape"
+    "latents.shape"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ff13a2cb",
+   "id": "6c732dbe",
    "metadata": {},
    "outputs": [],
    "source": [
     "generator.manual_seed(seed2)\n",
-    "noise2 = torch.randn((1, audio_diffusion.pipe.unet.in_channels,\n",
+    "latents2 = torch.randn((1, audio_diffusion.pipe.unet.in_channels,\n",
     "                      audio_diffusion.pipe.unet.sample_size[0],\n",
     "                      audio_diffusion.pipe.unet.sample_size[1]),\n",
     "                     generator=generator)\n",
-    "noise2.shape"
+    "latents2.shape"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bea26a5e",
+   "id": "159bcfc4",
    "metadata": {},
    "outputs": [],
    "source": [
     "alpha = 0.5  #@param {type:\"slider\", min:0, max:1, step:0.1}\n",
     "_, (sample_rate, audio3) = audio_diffusion.generate_spectrogram_and_audio(\n",
-    "    noise=audio_diffusion.pipe.slerp(noise, noise2, alpha),\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",
@@ -607,7 +607,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "60080eed",
+   "id": "ce6c9cc1",
    "metadata": {},
    "outputs": [],
    "source": []