{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!pip install SpeechRecognition pydub"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Bb_GmLxLYPSl",
        "outputId": "542a41c4-063d-4766-b2bc-9cab97080256"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting SpeechRecognition\n",
            "  Downloading speechrecognition-3.14.5-py3-none-any.whl.metadata (30 kB)\n",
            "Requirement already satisfied: pydub in /usr/local/lib/python3.12/dist-packages (0.25.1)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.12/dist-packages (from SpeechRecognition) (4.15.0)\n",
            "Downloading speechrecognition-3.14.5-py3-none-any.whl (32.9 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m32.9/32.9 MB\u001b[0m \u001b[31m22.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: SpeechRecognition\n",
            "Successfully installed SpeechRecognition-3.14.5\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from IPython.display import HTML, display\n",
        "import base64\n",
        "import json\n",
        "import numpy as np\n",
        "import soundfile as sf\n",
        "from google.colab import output\n",
        "\n",
        "RECORD = \"\"\"\n",
        "<button onclick=\"startRecording()\">🎤 Record</button>\n",
        "<button onclick=\"stopRecording()\">⏹ Stop</button>\n",
        "<script>\n",
        "let recorder;\n",
        "let audioChunks = [];\n",
        "\n",
        "async function startRecording() {\n",
        "  const stream = await navigator.mediaDevices.getUserMedia({ audio: true });\n",
        "  recorder = new MediaRecorder(stream);\n",
        "  audioChunks = [];\n",
        "  recorder.ondataavailable = e => audioChunks.push(e.data);\n",
        "  recorder.start();\n",
        "}\n",
        "\n",
        "async function stopRecording() {\n",
        "  recorder.stop();\n",
        "  recorder.onstop = async () => {\n",
        "    const blob = new Blob(audioChunks);\n",
        "    const buffer = await blob.arrayBuffer();\n",
        "    const base64data = btoa(\n",
        "      String.fromCharCode(...new Uint8Array(buffer))\n",
        "    );\n",
        "    google.colab.kernel.invokeFunction(\n",
        "      'notebook.save_audio',\n",
        "      [base64data],\n",
        "      {}\n",
        "    );\n",
        "  };\n",
        "}\n",
        "</script>\n",
        "\"\"\"\n",
        "\n",
        "display(HTML(RECORD))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 40
        },
        "id": "PhN27gCwYYxs",
        "outputId": "c30a588f-c16d-4d31-dd9e-383ba4c20697"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "<button onclick=\"startRecording()\">🎤 Record</button>\n",
              "<button onclick=\"stopRecording()\">⏹ Stop</button>\n",
              "<script>\n",
              "let recorder;\n",
              "let audioChunks = [];\n",
              "\n",
              "async function startRecording() {\n",
              "  const stream = await navigator.mediaDevices.getUserMedia({ audio: true });\n",
              "  recorder = new MediaRecorder(stream);\n",
              "  audioChunks = [];\n",
              "  recorder.ondataavailable = e => audioChunks.push(e.data);\n",
              "  recorder.start();\n",
              "}\n",
              "\n",
              "async function stopRecording() {\n",
              "  recorder.stop();\n",
              "  recorder.onstop = async () => {\n",
              "    const blob = new Blob(audioChunks);\n",
              "    const buffer = await blob.arrayBuffer();\n",
              "    const base64data = btoa(\n",
              "      String.fromCharCode(...new Uint8Array(buffer))\n",
              "    );\n",
              "    google.colab.kernel.invokeFunction(\n",
              "      'notebook.save_audio',\n",
              "      [base64data],\n",
              "      {}\n",
              "    );\n",
              "  };\n",
              "}\n",
              "</script>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def save_audio(base64data):\n",
        "    audio_bytes = base64.b64decode(base64data)\n",
        "    with open(\"audio.wav\", \"wb\") as f:\n",
        "        f.write(audio_bytes)\n",
        "\n",
        "output.register_callback('notebook.save_audio', save_audio)"
      ],
      "metadata": {
        "id": "hkVcUaEWYY1R"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import speech_recognition as sr\n",
        "from pydub import AudioSegment\n",
        "\n",
        "# Convert the audio file to a standard WAV format\n",
        "# The MediaRecorder might save in a format that speech_recognition doesn't natively handle\n",
        "try:\n",
        "    audio_file_path = \"audio.wav\"\n",
        "    sound = AudioSegment.from_file(audio_file_path)\n",
        "    sound.export(audio_file_path, format=\"wav\")\n",
        "except Exception as e:\n",
        "    print(f\"Error converting audio file: {e}\")\n",
        "\n",
        "r = sr.Recognizer()\n",
        "with sr.AudioFile(\"audio.wav\") as source:\n",
        "    audio = r.record(source)\n",
        "\n",
        "try:\n",
        "    text = r.recognize_google(audio, language=\"id-ID\")\n",
        "    print(\"Hasil Pengenalan:\", text)\n",
        "except sr.UnknownValueError:\n",
        "    print(\"Suara tidak dikenali\")\n",
        "except sr.RequestError as e:\n",
        "    print(f\"Could not request results from Google Speech Recognition service; {e}\")\n",
        "except Exception as e:\n",
        "    print(f\"An unexpected error occurred: {e}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_L5FGiYPYj9i",
        "outputId": "dea16927-be11-457d-bc44-f8baf5e02e3c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Hasil Pengenalan: data komputer komputer komputer\n"
          ]
        }
      ]
    }
  ]
}