adding quickstart notebook

README.md

@@ -42,6 +42,8 @@ Using an effect in your computation graph is as simple as calling the function w
 
 Here is a minimal example to demonstrate reverse engineering the drive value of a simple distortion effect using gradient descent. 
 
+Try it for yourself: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/csteinmetz1/dasp-pytorch/blob/main/examples/quickstart.ipynb)
+
 ```python
 import torch
 import torchaudio
@@ -56,7 +58,7 @@ x = x.unsqueeze(0)
 
 # apply some distortion with 16 dB drive
 drive = torch.tensor([16.0])
-y = dasp_pytorch.functional.distortion(x, drive)
+y = dasp_pytorch.functional.distortion(x, sr, drive)
 
 # create a parameter to optimizer
 drive_hat = torch.nn.Parameter(torch.tensor(0.0))
@@ -66,7 +68,7 @@ optimizer = torch.optim.Adam([drive_hat], lr=0.01)
 n_iters = 2500
 for n in range(n_iters):
     # apply distortion with the estimated parameter
-    y_hat = dasp_pytorch.functional.distortion(x, drive_hat)
+    y_hat = dasp_pytorch.functional.distortion(x, sr, drive_hat)
 
     # compute distance between estimate and target
     loss = torch.nn.functional.mse_loss(y_hat, y)
@@ -76,8 +78,9 @@ for n in range(n_iters):
     loss.backward()
     optimizer.step()
     print(
-        f"step: {n+1}/{n_iters}, loss: {loss.item():.3f}, drive: {drive_hat.item():.3f}"
+        f"step: {n+1}/{n_iters}, loss: {loss.item():.3e}, drive: {drive_hat.item():.3f}\r"
     )
+
 ```
 
 For the remaining examples we will use the [GuitarSet](https://guitarset.weebly.com/) dataset. 

examples/quickstart.ipynb

@@ -0,0 +1,95 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Q32l5f06ohtz"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install dasp-pytorch"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!wget https://csteinmetz1.github.io/sounds/assets/short_riff.wav"
+      ],
+      "metadata": {
+        "id": "MsHHumIypsAy"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import torch\n",
+        "import torchaudio\n",
+        "import dasp_pytorch"
+      ],
+      "metadata": {
+        "id": "VGSU9x2VojWg"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load audio\n",
+        "x, sr = torchaudio.load(\"short_riff.wav.1\")\n",
+        "\n",
+        "# create batch dim\n",
+        "# (batch_size, n_channels, n_samples)\n",
+        "x = x.unsqueeze(0)\n",
+        "\n",
+        "# apply some distortion with 16 dB drive\n",
+        "drive = torch.tensor([16.0])\n",
+        "y = dasp_pytorch.functional.distortion(x, sr, drive)\n",
+        "\n",
+        "# create a parameter to optimizer\n",
+        "drive_hat = torch.nn.Parameter(torch.tensor(0.0))\n",
+        "optimizer = torch.optim.Adam([drive_hat], lr=0.01)\n",
+        "\n",
+        "# optimize the parameter\n",
+        "n_iters = 2500\n",
+        "for n in range(n_iters):\n",
+        "    # apply distortion with the estimated parameter\n",
+        "    y_hat = dasp_pytorch.functional.distortion(x, sr, drive_hat)\n",
+        "\n",
+        "    # compute distance between estimate and target\n",
+        "    loss = torch.nn.functional.mse_loss(y_hat, y)\n",
+        "\n",
+        "    # optimize\n",
+        "    optimizer.zero_grad()\n",
+        "    loss.backward()\n",
+        "    optimizer.step()\n",
+        "    print(\n",
+        "        f\"step: {n+1}/{n_iters}, loss: {loss.item():.3e}, drive: {drive_hat.item():.3f}\\r\"\n",
+        "    )\n",
+        ""
+      ],
+      "metadata": {
+        "id": "MOhyTl3mopSi"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}