Create AudioClassificationgradio.ipynb

nbs/AudioClassificationgradio.ipynb

@@ -0,0 +1,682 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "AudioClassificationgradio.ipynb",
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "8e25e79ba0c34ac2a39504d2bdb23a44": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_c326c94972544c0cafd0aec1424d3d66",
+              "IPY_MODEL_a5ded79eb6274a2693d4f6f46dbdaae6",
+              "IPY_MODEL_9165407f88a44866a6372082c5a1bdd1"
+            ],
+            "layout": "IPY_MODEL_cd13120cc6f345ff958b3438a51d9caf"
+          }
+        },
+        "c326c94972544c0cafd0aec1424d3d66": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_358da8bada514630b9078cd49fb2b2dc",
+            "placeholder": "​",
+            "style": "IPY_MODEL_53a416f6a7e9499ea6a88e44f2087c0d",
+            "value": "Downloading: 100%"
+          }
+        },
+        "a5ded79eb6274a2693d4f6f46dbdaae6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_74ce31440c4c497cb1ff10748a39c9e0",
+            "max": 103192469,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_908199f1d2244909bd58c3bc46e6a47f",
+            "value": 103192469
+          }
+        },
+        "9165407f88a44866a6372082c5a1bdd1": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_3efa06b0aafd4f2ea01ebfc0a7d6abe6",
+            "placeholder": "​",
+            "style": "IPY_MODEL_10ed9d0b19814111b80a281ea80f60d9",
+            "value": " 103M/103M [00:02<00:00, 51.8MB/s]"
+          }
+        },
+        "cd13120cc6f345ff958b3438a51d9caf": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "358da8bada514630b9078cd49fb2b2dc": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "53a416f6a7e9499ea6a88e44f2087c0d": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "74ce31440c4c497cb1ff10748a39c9e0": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "908199f1d2244909bd58c3bc46e6a47f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "3efa06b0aafd4f2ea01ebfc0a7d6abe6": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "10ed9d0b19814111b80a281ea80f60d9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        }
+      }
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tj_BVh5omaoQ",
+        "outputId": "413b2cf4-f8da-4bb3-a0a3-1c58cd89cfa0"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[K     |████████████████████████████████| 197 kB 24.3 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 2.9 MB 52.4 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 77 kB 5.4 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 60 kB 6.1 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 84 kB 3.1 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 54 kB 2.7 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 1.1 MB 40.9 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 2.0 MB 42.1 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 253 kB 54.9 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 53 kB 2.1 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 212 kB 44.2 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 271 kB 64.4 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 144 kB 45.5 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 94 kB 3.1 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 58 kB 6.2 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 10.9 MB 53.7 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 79 kB 7.1 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 43 kB 1.8 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 62 kB 953 kB/s \n",
+            "\u001b[K     |████████████████████████████████| 856 kB 47.5 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 4.0 MB 58.7 MB/s \n",
+            "\u001b[K     |████████████████████████████████| 58 kB 6.0 MB/s \n",
+            "\u001b[?25h  Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Building wheel for python-multipart (setup.py) ... \u001b[?25l\u001b[?25hdone\n"
+          ]
+        }
+      ],
+      "source": [
+        "! pip install -Uqq fastai gradio torchaudio torchvision huggingface_hub"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import gradio\n",
+        "import torchaudio\n",
+        "from fastai.vision.all import *\n",
+        "from fastai.learner import load_learner\n",
+        "from torchvision.utils import save_image\n",
+        "from huggingface_hub import hf_hub_download"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "xIM_o4w-ms2J",
+        "outputId": "936b730f-2d52-4cc2-fd7a-afbf86d05687"
+      },
+      "execution_count": 2,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.7/dist-packages/paramiko/transport.py:236: CryptographyDeprecationWarning: Blowfish has been deprecated\n",
+            "  \"class\": algorithms.Blowfish,\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model = load_learner(\n",
+        "    hf_hub_download(\"kurianbenoy/music_genre_classification_baseline\", \"model.pkl\")\n",
+        ")\n",
+        "\n",
+        "labels = model.dls.vocab"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 49,
+          "referenced_widgets": [
+            "8e25e79ba0c34ac2a39504d2bdb23a44",
+            "c326c94972544c0cafd0aec1424d3d66",
+            "a5ded79eb6274a2693d4f6f46dbdaae6",
+            "9165407f88a44866a6372082c5a1bdd1",
+            "cd13120cc6f345ff958b3438a51d9caf",
+            "358da8bada514630b9078cd49fb2b2dc",
+            "53a416f6a7e9499ea6a88e44f2087c0d",
+            "74ce31440c4c497cb1ff10748a39c9e0",
+            "908199f1d2244909bd58c3bc46e6a47f",
+            "3efa06b0aafd4f2ea01ebfc0a7d6abe6",
+            "10ed9d0b19814111b80a281ea80f60d9"
+          ]
+        },
+        "id": "MJxNnlsYmwsJ",
+        "outputId": "3ba1eca7-1986-4f29-a549-b51bb79a4c88"
+      },
+      "execution_count": 3,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Downloading:   0%|          | 0.00/103M [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "8e25e79ba0c34ac2a39504d2bdb23a44"
+            }
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "N_FFT = 2048\n",
+        "HOP_LEN = 1024\n",
+        "\n",
+        "\n",
+        "def create_spectrogram(filename):\n",
+        "    audio, sr = torchaudio.load(filename)\n",
+        "    specgram = torchaudio.transforms.MelSpectrogram(\n",
+        "        sample_rate=sr,\n",
+        "        n_fft=N_FFT,\n",
+        "        win_length=N_FFT,\n",
+        "        hop_length=HOP_LEN,\n",
+        "        center=True,\n",
+        "        pad_mode=\"reflect\",\n",
+        "        power=2.0,\n",
+        "        norm=\"slaney\",\n",
+        "        onesided=True,\n",
+        "        n_mels=224,\n",
+        "        mel_scale=\"htk\",\n",
+        "    )(audio).mean(axis=0)\n",
+        "    specgram = torchaudio.transforms.AmplitudeToDB()(specgram)\n",
+        "    specgram = specgram - specgram.min()\n",
+        "    specgram = specgram / specgram.max()\n",
+        "\n",
+        "    return specgram"
+      ],
+      "metadata": {
+        "id": "J1Goh5DHnm59"
+      },
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def create_image(filename):\n",
+        "    specgram = create_spectrogram(filename)\n",
+        "    dest = Path(\"temp.png\")\n",
+        "    save_image(specgram, \"temp.png\")"
+      ],
+      "metadata": {
+        "id": "-J15K2MmqADm"
+      },
+      "execution_count": 11,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def predict(img):\n",
+        "    img = PILImage.create(img)\n",
+        "    _pred, _pred_w_idx, probs = model.predict(img)\n",
+        "    labels_probs = {labels[i]: float(probs[i]) for i, _ in enumerate(labels)}\n",
+        "    return labels_probs"
+      ],
+      "metadata": {
+        "id": "1cOhBdp0m2Q5"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def end2endpipeline(filename):\n",
+        "    create_image(filename)\n",
+        "    return predict(\"temp.png\")"
+      ],
+      "metadata": {
+        "id": "eXIEc4blqOWQ"
+      },
+      "execution_count": 12,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "interface_options = {\n",
+        "    \"title\": \"Music Genre Classification\",\n",
+        "    \"description\": \"A simple baseline model for classifying music genres with fast.ai on [Kaggle competition data](https://www.kaggle.com/competitions/kaggle-pog-series-s01e02/data)\",\n",
+        "    \"interpretation\": \"default\",\n",
+        "    \"layout\": \"horizontal\",\n",
+        "    \"theme\": \"default\",\n",
+        "}\n",
+        "\n",
+        "demo = gradio.Interface(\n",
+        "    fn=end2endpipeline,\n",
+        "    inputs=gradio.inputs.Audio(source=\"microphone\", type=\"filepath\", label=\"Record/ Drop audio\"),\n",
+        "    outputs=gradio.outputs.Label(num_top_classes=5),\n",
+        "    **interface_options,\n",
+        ")\n",
+        "\n",
+        "launch_options = {\n",
+        "    \"enable_queue\": True,\n",
+        "    \"share\": False,\n",
+        "}\n",
+        "demo.launch(**launch_options)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 662
+        },
+        "id": "uMO5CynZm_pL",
+        "outputId": "0cff073a-293d-4c3d-d3bf-a924d63cdfec"
+      },
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Colab notebook detected. To show errors in colab notebook, set `debug=True` in `launch()`\n",
+            "Your interface requires microphone or webcam permissions - this may cause issues in Colab. Use the External URL in case of issues.\n",
+            "Running on public URL: https://55955.gradio.app\n",
+            "\n",
+            "This share link expires in 72 hours. For free permanent hosting, check out Spaces (https://huggingface.co/spaces)\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.lib.display.IFrame at 0x7f647af3b450>"
+            ],
+            "text/html": [
+              "\n",
+              "        <iframe\n",
+              "            width=\"900\"\n",
+              "            height=\"500\"\n",
+              "            src=\"https://55955.gradio.app\"\n",
+              "            frameborder=\"0\"\n",
+              "            allowfullscreen\n",
+              "        ></iframe>\n",
+              "        "
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(<fastapi.applications.FastAPI at 0x7f65bf011ed0>,\n",
+              " 'http://127.0.0.1:7862/',\n",
+              " 'https://55955.gradio.app')"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 13
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "input_audio = [gradio.inputs.Audio(source=\"microphone\", type=\"filepath\", label=\"Record/ Drop audio\")]\n",
+        "input_audio"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "8Ptz2HMdnAE7",
+        "outputId": "2cac3314-07eb-4c91-d5ed-770e2ed6ae0d"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "[Audio(label=\"Record/ Drop audio\")]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 9
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        ""
+      ],
+      "metadata": {
+        "id": "_wHGGfNfnufy"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}