chore: import upstream snapshot with attribution

2026-07-13 13:25:10 +08:00
commit c397331b1e
3684 changed files with 990993 additions and 0 deletions
@@ -0,0 +1,34 @@
+# FunASR Colab Quickstart
+
+English | [简体中文](README_zh.md) | [日本語](README_ja.md) | [한국어](README_ko.md)
+
+Run FunASR in a browser without preparing a local Python environment.
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb)
+
+## What the notebook covers
+
+- Install FunASR and runtime dependencies in Colab.
+- Pick `cuda:0` automatically when a Colab GPU is available, otherwise use CPU.
+- Transcribe a public sample audio file with `paraformer-zh`, VAD, and punctuation.
+- Upload your own audio file and run the same model.
+- Save the transcript JSON for sharing or issue reports.
+
+## Notes
+
+- The first run downloads model files and may take a few minutes.
+- CPU runtime works for a quick smoke test; GPU runtime is faster for longer audio.
+- If you are evaluating production deployment, use the [deployment matrix](../../docs/deployment_matrix.md) after the notebook works.
+- For OpenAI-compatible HTTP service testing, use [examples/openai_api](../openai_api/).
+
+## Troubleshooting
+
+| Symptom | What to try |
+|---|---|
+| Colab runtime disconnects or resets | Reconnect the runtime, rerun the install cell, then rerun the model cell. The notebook does not persist Python packages across runtime resets. |
+| GPU is unavailable | Use `Runtime > Change runtime type > GPU`. If no GPU is assigned, the notebook still works on CPU for a short smoke test. |
+| Model download is slow | Rerun the cell after the network recovers. The first run downloads model files and later runs in the same runtime are faster. |
+| Uploaded audio fails or is too large | Try a short WAV/MP3 first. For long files, trim a representative sample before using Colab. |
+| Output is unexpected | Save the transcript JSON cell output and include it when opening an issue. |
+
+Notebook source: [funasr_quickstart.ipynb](https://github.com/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb).
@@ -0,0 +1,34 @@
+# FunASR Colab クイックスタート
+
+[English](README.md) | [简体中文](README_zh.md) | 日本語 | [한국어](README_ko.md)
+
+ローカルの Python 環境を準備せずに、ブラウザだけで FunASR を実行できます。
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb)
+
+## Notebook で試せること
+
+- Colab に FunASR と実行時依存関係をインストールします。
+- Colab の GPU が使える場合は自動で `cuda:0` を選び、なければ CPU を使います。
+- `paraformer-zh`、VAD、句読点モデルで公開サンプル音声を文字起こしします。
+- 自分の音声ファイルをアップロードし、同じモデルで文字起こしします。
+- transcript JSON を保存し、共有、比較、issue 報告に利用できます。
+
+## 利用メモ
+
+- 初回実行ではモデルファイルをダウンロードするため、数分かかる場合があります。
+- CPU runtime は短い smoke test に使えます。長い音声では GPU runtime の方が高速です。
+- 本番デプロイを評価する場合は、notebook が動いた後に [deployment matrix](../../docs/deployment_matrix.md) を確認してください。
+- OpenAI 互換 HTTP サービスを試す場合は [examples/openai_api](../openai_api/README_ja.md) を利用してください。
+
+## トラブルシューティング
+
+| 症状 | 対処 |
+|---|---|
+| Colab runtime が切断またはリセットされる | runtime に再接続し、install cell を実行してから model cell を再実行します。runtime リセット後は Python パッケージが保持されません。 |
+| GPU が使えない | `Runtime > Change runtime type > GPU` に変更します。GPU が割り当てられない場合でも、短い smoke test は CPU で実行できます。 |
+| モデルのダウンロードが遅い | ネットワークが回復してから cell を再実行します。初回はモデルファイルをダウンロードし、同じ runtime の後続実行は速くなります。 |
+| アップロードした音声が失敗する、または大きすぎる | まず短い WAV/MP3 で確認してください。長い音声は代表的な区間に切り出してから Colab で試します。 |
+| 出力が期待と違う | transcript JSON cell の出力を保存し、issue を作成するときに添付してください。 |
+
+Notebook source: [funasr_quickstart.ipynb](https://github.com/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb).
@@ -0,0 +1,34 @@
+# FunASR Colab 빠른 시작
+
+[English](README.md) | [简体中文](README_zh.md) | [日本語](README_ja.md) | 한국어
+
+로컬 Python 환경을 준비하지 않고 브라우저에서 바로 FunASR을 실행할 수 있습니다.
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb)
+
+## Notebook에서 확인할 수 있는 것
+
+- Colab에 FunASR과 런타임 의존성을 설치합니다.
+- Colab GPU가 있으면 자동으로 `cuda:0`을 사용하고, 없으면 CPU를 사용합니다.
+- `paraformer-zh`, VAD, 문장부호 모델로 공개 샘플 오디오를 전사합니다.
+- 직접 업로드한 오디오 파일을 같은 모델로 전사합니다.
+- transcript JSON을 저장하여 공유, 비교, issue 보고에 활용할 수 있습니다.
+
+## 사용 메모
+
+- 첫 실행에서는 모델 파일을 다운로드하므로 몇 분이 걸릴 수 있습니다.
+- CPU runtime은 짧은 smoke test에 적합합니다. 긴 오디오에는 GPU runtime이 더 빠릅니다.
+- 프로덕션 배포를 검토하려면 notebook을 먼저 실행한 뒤 [deployment matrix](../../docs/deployment_matrix.md)를 확인하세요.
+- OpenAI 호환 HTTP 서비스를 테스트하려면 [examples/openai_api](../openai_api/README_ko.md)를 사용하세요.
+
+## 문제 해결
+
+| 증상 | 해결 방법 |
+|---|---|
+| Colab runtime이 끊기거나 재설정됨 | runtime에 다시 연결한 뒤 install cell을 먼저 실행하고 model cell을 다시 실행하세요. runtime이 재설정되면 설치된 Python 패키지가 유지되지 않습니다. |
+| GPU를 사용할 수 없음 | `Runtime > Change runtime type > GPU`로 변경하세요. GPU가 배정되지 않아도 짧은 smoke test는 CPU로 실행할 수 있습니다. |
+| 모델 다운로드가 느림 | 네트워크가 안정된 뒤 cell을 다시 실행하세요. 첫 실행은 모델 파일을 다운로드하며, 같은 runtime의 이후 실행은 더 빠릅니다. |
+| 업로드한 오디오가 실패하거나 너무 큼 | 먼저 짧은 WAV/MP3로 확인하세요. 긴 오디오는 대표 구간을 잘라 Colab에서 테스트하는 것이 좋습니다. |
+| 출력이 예상과 다름 | transcript JSON cell 출력을 저장하고 issue를 열 때 함께 첨부하세요. |
+
+Notebook source: [funasr_quickstart.ipynb](https://github.com/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb).
@@ -0,0 +1,34 @@
+# FunASR Colab 快速体验
+
+[English](README.md) | 简体中文 | [日本語](README_ja.md) | [한국어](README_ko.md)
+
+无需提前配置本地 Python 环境，直接在浏览器里运行 FunASR。
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb)
+
+## Notebook 覆盖内容
+
+- 在 Colab 中安装 FunASR 和运行依赖。
+- 如果 Colab runtime 有 GPU，自动使用 `cuda:0`；否则使用 CPU。
+- 使用 `paraformer-zh`、VAD 和标点模型转写公开样例音频。
+- 上传自己的音频文件，并用同一套模型运行转写。
+- 保存 transcript JSON，便于分享、对比或提交 issue。
+
+## 使用建议
+
+- 第一次运行会下载模型文件，可能需要几分钟。
+- CPU runtime 适合快速 smoke test；长音频建议切换到 GPU runtime。
+- 如果要评估生产部署，先跑通 notebook，再阅读 [部署选型表](../../docs/deployment_matrix_zh.md)。
+- 如果要测试 OpenAI 兼容 HTTP 服务，请使用 [examples/openai_api](../openai_api/README_zh.md)。
+
+## 故障排查
+
+| 现象 | 处理方式 |
+|---|---|
+| Colab runtime 断开或重置 | 重新连接 runtime，先重跑安装单元，再重跑模型单元。runtime 重置后不会保留已安装的 Python 包。 |
+| 没有 GPU | 通过 `Runtime > Change runtime type > GPU` 切换。没有分配到 GPU 时，短音频 smoke test 仍可用 CPU 跑通。 |
+| 模型下载很慢 | 网络恢复后重跑该单元。第一次运行会下载模型文件，同一个 runtime 后续运行会更快。 |
+| 上传音频失败或文件太大 | 先用短 WAV/MP3 验证。长音频建议截取有代表性的片段再放到 Colab。 |
+| 输出不符合预期 | 保存 transcript JSON 单元输出，提交 issue 时一起附上。 |
+
+Notebook 源文件：[funasr_quickstart.ipynb](https://github.com/modelscope/FunASR/blob/main/examples/colab/funasr_quickstart.ipynb)。
@@ -0,0 +1,160 @@
+{
+  "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
+}