Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

4.5 KB
Raw Blame
{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# FunASR Colab Quickstart\n",
        "\n",
        "Run FunASR in a browser, transcribe a public sample, then try your own audio file.\n",
        "\n",
        "Repository: https://github.com/modelscope/FunASR\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 1. Install dependencies\n",
        "\n",
        "The first cell can take a few minutes because it installs FunASR and downloads Python wheels. Colab already includes PyTorch in most runtimes.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "!pip -q install -U funasr modelscope soundfile"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 2. Select CPU or GPU\n",
        "\n",
        "For a faster run, choose **Runtime -> Change runtime type -> GPU** in Colab before running the notebook.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "import json\n",
        "import torch\n",
        "\n",
        "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
        "print(f\"Using device: {device}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 3. Transcribe a public sample\n",
        "\n",
        "This uses `paraformer-zh` with VAD and punctuation so the example works with a short public Mandarin sample.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from funasr import AutoModel\n",
        "\n",
        "sample_url = \"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav\"\n",
        "\n",
        "model = AutoModel(\n",
        "    model=\"paraformer-zh\",\n",
        "    vad_model=\"fsmn-vad\",\n",
        "    punc_model=\"ct-punc\",\n",
        "    device=device,\n",
        ")\n",
        "\n",
        "result = model.generate(input=sample_url, batch_size_s=60)\n",
        "print(json.dumps(result, ensure_ascii=False, indent=2))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 4. Try your own audio file\n",
        "\n",
        "Upload a short `.wav`, `.mp3`, `.m4a`, or `.flac` file. For long recordings, split the audio or use a GPU runtime.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from google.colab import files\n",
        "\n",
        "uploaded = files.upload()\n",
        "audio_path = next(iter(uploaded))\n",
        "print(f\"Uploaded: {audio_path}\")\n",
        "\n",
        "user_result = model.generate(input=audio_path, batch_size_s=60)\n",
        "print(json.dumps(user_result, ensure_ascii=False, indent=2))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## 5. Save the transcript JSON\n",
        "\n",
        "Attach this JSON when you open a GitHub issue or compare model outputs.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "from pathlib import Path\n",
        "\n",
        "Path(\"funasr_transcript.json\").write_text(\n",
        "    json.dumps(user_result, ensure_ascii=False, indent=2),\n",
        "    encoding=\"utf-8\",\n",
        ")\n",
        "files.download(\"funasr_transcript.json\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Next steps\n",
        "\n",
        "- Choose a model: https://github.com/modelscope/FunASR/blob/main/docs/model_selection.md\n",
        "- Compare with Whisper or cloud ASR: https://github.com/modelscope/FunASR/blob/main/docs/migration_from_whisper.md\n",
        "- Deploy an OpenAI-compatible API: https://github.com/modelscope/FunASR/tree/main/examples/openai_api\n",
        "- Read production deployment options: https://github.com/modelscope/FunASR/blob/main/docs/deployment_matrix.md\n"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}