docs: make native Transformers the Nano adoption path

README.md

@@ -29,6 +29,14 @@
 
 ## Quick Start
 
+### Native Transformers
+
+For Fun-ASR-Nano transcription with the Hugging Face API, start with the [Transformers 5.17.0 CPU quickstart](./docs/transformers_native.md). No FunASR toolkit or remote Python code is needed.
+
+[Space](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano) · [Notebook](https://colab.research.google.com/github/QwenAudio/Fun-ASR/blob/main/examples/colab/fun_asr_nano_transformers.ipynb) · [Python / batch examples](https://github.com/QwenAudio/Fun-ASR/tree/main/examples/transformers)
+
+### FunASR toolkit and pipelines
+
 [![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)
 
 No local setup? Open the [Colab quickstart](./examples/colab/) to transcribe a public sample or upload your own audio in a browser.
@@ -55,7 +63,7 @@ PY
 Only use `device="cuda"` when this prints `True`; otherwise use `device="cpu"`
 or reinstall PyTorch with the correct CUDA wheel.
 
-**Flagship model — Fun-ASR-Nano** (LLM-ASR for Chinese, English, and Japanese, plus Chinese dialect groups and regional accents; needs a GPU):
+**FunASR toolkit GPU example: Fun-ASR-Nano** (Chinese, English, Japanese, and Chinese dialect groups and regional accents; the separate native Transformers CPU path is linked above):
 
 ```python
 from funasr import AutoModel
@@ -357,7 +365,7 @@ recordings with the same evaluation scope.
 
 - **MOSS-Transcribe-Diarize** brings long-form ASR, timestamps, and anonymous speaker labels to FunASR services, Docker, Kubernetes, vLLM/SGLang workflows, and FunClip. [Deploy MOSS ->](./docs/moss_transcribe_diarize.md)
 - **FunASR 1.4.15** adds tested NumPy 2 compatibility and fixes streaming KWS/VAD boundaries and checkpoint ranking. Install with `python -m pip install -U "funasr==1.4.15"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.15)
-- **Native Transformers:** Fun-ASR-Nano [merged upstream](https://github.com/huggingface/transformers/pull/46180). Use the official `-hf` checkpoint and pinned source; stable 5.16.1 does not include it. [Installation and inference ->](./docs/transformers_native.md)
+- **Native Transformers:** Released **5.17.0** supports Fun-ASR-Nano with the official `-hf` checkpoint, CPU examples and a notebook. [Get started ->](./docs/transformers_native.md)
 
 > See [GitHub Releases](https://github.com/modelscope/FunASR/releases) for the complete changelog and downloadable assets.
 

README_ja.md

@@ -30,6 +30,14 @@
 
 ## クイックスタート
 
+### ネイティブ Transformers
+
+Hugging Face API で Fun-ASR-Nano を使う場合は [Transformers 5.17.0 CPU ガイド（英語）](./docs/transformers_native.md) から開始できます。FunASR toolkit とリモート Python コードは不要です。
+
+[Space](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano) · [Notebook](https://colab.research.google.com/github/QwenAudio/Fun-ASR/blob/main/examples/colab/fun_asr_nano_transformers.ipynb) · [Python / batch examples](https://github.com/QwenAudio/Fun-ASR/tree/main/examples/transformers)
+
+### FunASR toolkit とパイプライン
+
 ```bash
 python -m pip install torch torchaudio
 python -m pip install funasr
@@ -105,7 +113,7 @@ CER/WER をそろえて比較してください。オフラインのスループ
 
 - **MOSS-Transcribe-Diarize** を FunASR service、Docker、Kubernetes、vLLM/SGLang workflow、FunClip に統合し、長時間 ASR、timestamp、匿名 speaker label を一度に処理できます。[MOSS をデプロイ ->](./docs/moss_transcribe_diarize.md)
 - **FunASR 1.4.15** はテスト済みの NumPy 2 互換性を追加し、ストリーミング KWS/VAD の境界処理と checkpoint の順位付けを修正します。`python -m pip install -U "funasr==1.4.15"`。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.15)
-- **ネイティブ Transformers：** Fun-ASR-Nano が[上流にマージ](https://github.com/huggingface/transformers/pull/46180)されました。公式 `-hf` checkpoint と固定ソースを使用します。安定版 5.16.1 には未収録です。[導入ガイド（英語） ->](./docs/transformers_native.md)
+- **ネイティブ Transformers：** 正式版 **5.17.0** が Fun-ASR-Nano に対応。公式 `-hf` checkpoint、CPU サンプル、Notebook：[導入ガイド（英語） ->](./docs/transformers_native.md)
 
 > 完全な変更履歴と download asset は [GitHub Releases](https://github.com/modelscope/FunASR/releases) を参照してください。
 

README_ko.md

@@ -30,6 +30,14 @@
 
 ## 빠른 시작
 
+### 네이티브 Transformers
+
+Hugging Face API로 Fun-ASR-Nano를 사용하려면 [Transformers 5.17.0 CPU 가이드(영문)](./docs/transformers_native.md)에서 시작하세요. FunASR toolkit이나 원격 Python 코드가 필요 없습니다.
+
+[Space](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano) · [Notebook](https://colab.research.google.com/github/QwenAudio/Fun-ASR/blob/main/examples/colab/fun_asr_nano_transformers.ipynb) · [Python / batch examples](https://github.com/QwenAudio/Fun-ASR/tree/main/examples/transformers)
+
+### FunASR toolkit 및 파이프라인
+
 ```bash
 python -m pip install torch torchaudio
 python -m pip install funasr
@@ -104,7 +112,7 @@ checkpoint/revision, 오디오 집합, 하드웨어, 배치, 워밍업, 측정 
 
 - **MOSS-Transcribe-Diarize**를 FunASR service, Docker, Kubernetes, vLLM/SGLang workflow, FunClip에 통합해 긴 오디오 ASR, timestamp, 익명 speaker label을 한 번에 처리합니다. [MOSS 배포 ->](./docs/moss_transcribe_diarize.md)
 - **FunASR 1.4.15**는 테스트를 거친 NumPy 2 호환성을 추가하고 스트리밍 KWS/VAD 경계 처리와 checkpoint 순위 산정을 수정합니다. `python -m pip install -U "funasr==1.4.15"`. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.15)
-- **네이티브 Transformers:** Fun-ASR-Nano가 [업스트림에 병합](https://github.com/huggingface/transformers/pull/46180)되었습니다. 공식 `-hf` checkpoint와 고정 소스를 사용하세요. 안정 버전 5.16.1에는 아직 포함되지 않았습니다. [설치 가이드(영문) ->](./docs/transformers_native.md)
+- **네이티브 Transformers:** 정식 버전 **5.17.0**이 Fun-ASR-Nano를 지원합니다. 공식 `-hf` checkpoint, CPU 예제, Notebook: [설치 가이드(영문) ->](./docs/transformers_native.md)
 
 > 전체 변경 기록과 download asset은 [GitHub Releases](https://github.com/modelscope/FunASR/releases)에서 확인할 수 있습니다.
 

README_zh.md

@@ -28,6 +28,14 @@
 
 ## 快速开始
 
+### 原生 Transformers
+
+使用 Hugging Face API 转写 Fun-ASR-Nano，先看 [Transformers 5.17.0 CPU 快速开始](./docs/transformers_native_zh.md)，不需要安装 FunASR 工具库或执行远程 Python 代码。
+
+[Space](https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano) · [Notebook](https://colab.research.google.com/github/QwenAudio/Fun-ASR/blob/main/examples/colab/fun_asr_nano_transformers.ipynb) · [Python / batch examples](https://github.com/QwenAudio/Fun-ASR/tree/main/examples/transformers)
+
+### FunASR 工具库与流水线
+
 [![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)
 
 不想先配置本地环境？可以打开 [Colab 快速体验](./examples/colab/README_zh.md) 在浏览器里转写公开样例或上传自己的音频。
@@ -150,7 +158,7 @@ checkpoint/revision、音频集、硬件、批量大小、预热、计时范围
 
 - **MOSS-Transcribe-Diarize** 已接入 FunASR 服务、Docker、Kubernetes、vLLM/SGLang 工作流和 FunClip，一次完成长音频转写、时间戳与匿名说话人标注。[部署 MOSS ->](./docs/moss_transcribe_diarize_zh.md)
 - **FunASR 1.4.15** 新增经过测试的 NumPy 2 兼容支持，修复流式 KWS/VAD 边界处理和 checkpoint 排序。升级命令：`python -m pip install -U "funasr==1.4.15"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.15)
-- **原生 Transformers：** Fun-ASR-Nano [已合入上游](https://github.com/huggingface/transformers/pull/46180)。使用官方 `-hf` checkpoint 与固定源码；稳定版 5.16.1 尚未包含。[安装与推理 ->](./docs/transformers_native_zh.md)
+- **原生 Transformers：** 正式版 **5.17.0** 已支持 Fun-ASR-Nano。官方 `-hf` 权重、CPU 示例与 Notebook：[安装与推理 ->](./docs/transformers_native_zh.md)
 
 > 完整改动记录和可下载资产请查看 [GitHub Releases](https://github.com/modelscope/FunASR/releases)。
 

docs/deployment_matrix.md

@@ -6,7 +6,7 @@ Use this page to choose the shortest deployment path for a product, demo, benchm
 
 | Path | Best for | Start here | Operational notes |
 |---|---|---|---|
-| Native Transformers | Python applications using Hugging Face processors and generation | [Native Fun-ASR-Nano guide](./transformers_native.md) | Official `-hf` checkpoint and pinned source; stable 5.16.1 lacks support at the 2026-09-09 check. Python inference, not an HTTP or realtime server. |
+| Native Transformers | First Nano transcript, notebooks and Hugging Face Python applications | [Native Fun-ASR-Nano guide](./transformers_native.md) | Released **5.17.0**, official `-hf` checkpoint, CPU examples and batching. Python inference, not an HTTP or realtime server. |
 | Colab notebook | Browser smoke tests, first evaluation, shareable demos | [Colab quickstart](../examples/colab/) | No local setup; first run downloads model files, GPU runtime is faster. |
 | Python API | Notebooks, offline jobs, first model evaluation | [README quick start](../README.md#quick-start) | Lowest ceremony; caller owns batching, retries, and files. |
 | OpenAI-compatible API | Private speech API, agents, Dify/LangChain/AutoGen-style clients | [OpenAI API example](../examples/openai_api/) | Easiest integration for apps that already support OpenAI audio APIs. |

docs/deployment_matrix_ja.md

@@ -1,5 +1,9 @@
 # FunASR デプロイ選択マトリクス
 
+## Transformers で Nano を試す
+
+中国語・英語・日本語の文字起こしには [Transformers 5.17.0 ガイド（英語）](./transformers_native.md) と公式 `FunAudioLLM/Fun-ASR-Nano-2512-hf` checkpoint を使えます。CPU サンプルがあり、toolkit とサービスの経路は別です。ネイティブ出力はテキストで、タイムスタンプ・話者・HTTP サーバーを追加しません。
+
 プロダクト、デモ、ベンチマーク、社内ワークフローに合わせて最短のデプロイ経路を選ぶためのガイドです。まずは要件を満たす最小構成から始め、throughput、latency、integration 要件が明確になったら重い runtime に移行してください。
 
 ## クイック判断表

docs/deployment_matrix_ko.md

@@ -1,5 +1,9 @@
 # FunASR 배포 선택 매트릭스
 
+## Transformers로 Nano 시작하기
+
+중국어·영어·일본어 전사는 [Transformers 5.17.0 가이드(영문)](./transformers_native.md)와 공식 `FunAudioLLM/Fun-ASR-Nano-2512-hf` checkpoint로 시작할 수 있습니다. CPU 예제가 있으며 toolkit과 서비스 경로는 별도입니다. 네이티브 출력은 텍스트이며 타임스탬프·화자·HTTP 서버를 추가하지 않습니다.
+
 제품, 데모, 벤치마크, 내부 워크플로에 맞는 가장 짧은 배포 경로를 고르기 위한 가이드입니다. 먼저 요구를 만족하는 최소 구성에서 시작하고, throughput, latency, integration 요구가 명확해질 때 더 무거운 runtime으로 이동하세요.
 
 ## 빠른 결정 표

docs/deployment_matrix_zh.md

@@ -6,7 +6,7 @@
 
 | 路径 | 适合场景 | 从这里开始 | 运维提示 |
 |---|---|---|---|
-| 原生 Transformers | 已使用 Hugging Face 处理器与生成接口的 Python 应用 | [原生 Fun-ASR-Nano 指南](./transformers_native_zh.md) | 官方 `-hf` checkpoint 与固定源码；2026-09-09 核验的稳定版 5.16.1 尚未包含。是 Python 推理入口，不是 HTTP 或实时服务器。 |
+| 原生 Transformers | Nano 首次转写、Notebook 与 Hugging Face Python 应用 | [原生 Fun-ASR-Nano 指南](./transformers_native_zh.md) | 正式版 **5.17.0**，官方 `-hf` checkpoint，CPU 与批处理示例。是 Python 推理入口，不是 HTTP 或实时服务器。 |
 | Colab Notebook | 浏览器 smoke test、首次评估、可分享 demo | [Colab 快速体验](../examples/colab/README_zh.md) | 不需要本地环境；首次运行会下载模型，GPU runtime 更快。 |
 | Python API | Notebook、离线任务、首次模型评测 | [README 快速开始](../README_zh.md#快速开始) | 最简单；调用方自己负责批处理、重试和文件管理。 |
 | OpenAI 兼容 API | 私有语音 API、Agent、Dify/LangChain/AutoGen 风格客户端 | [OpenAI API 示例](../examples/openai_api/README_zh.md) | 已支持 OpenAI audio API 的应用最容易接入。 |

docs/index.rst

@@ -12,6 +12,8 @@ entry to these guides. Source Markdown remains in this repository.
    :maxdepth: 1
    :caption: Get Started
 
+   transformers_native
+   transformers_native_zh
    installation/installation
    installation/installation_zh
    installation/docker

docs/installation/installation.md

@@ -2,6 +2,8 @@
 
 # Install the Python SDK
 
+> **Only need native Fun-ASR-Nano transcription?** Start with [Transformers 5.17.0](../transformers_native.md). It loads the separate `-hf` checkpoint without the FunASR toolkit. This page covers the `funasr.AutoModel` toolkit path; do not mix dependencies, parameters or output contracts.
+
 Use this guide for `from funasr import AutoModel`. For a packaged C++ service, start with [Docker and runtime images](./docker.md). After installation, continue to the [SDK tutorial](../tutorial/README.md).
 
 ## 1. Create an isolated environment

docs/installation/installation_zh.md

@@ -2,6 +2,8 @@
 
 # 安装 Python SDK
 
+> **只需 Fun-ASR-Nano 原生推理？** 使用 [Transformers 5.17.0 快速开始](../transformers_native_zh.md)。它加载独立的 `-hf` 权重，不要求 FunASR 工具库。本页保留 `funasr.AutoModel` 工具库路径，两者的依赖、参数和输出不可混用。
+
 本页适用于 `from funasr import AutoModel`。需要打包好的 C++ 服务时，请先看 [Docker 与运行时镜像](./docker_zh.md)。安装完成后进入 [SDK 教程](../tutorial/README_zh.md)。
 
 ## 1. 创建独立环境

docs/model_selection.md

@@ -1,5 +1,9 @@
 # FunASR Model Selection Guide
 
+## Transformers-first Nano evaluation
+
+For Chinese, English and Japanese transcription through Hugging Face APIs, start with [native Transformers 5.17.0](./transformers_native.md), the official `FunAudioLLM/Fun-ASR-Nano-2512-hf` checkpoint and the CPU example. The toolkit and service paths below remain separate; the native export does not add timestamps, speakers or an HTTP endpoint.
+
 Use this guide when you are choosing a first model, comparing FunASR with Whisper or a cloud ASR provider, or deciding which model alias to expose through the OpenAI-compatible API.
 
 ## Fast default path

docs/model_selection_ja.md

@@ -1,5 +1,9 @@
 # FunASR モデル選択ガイド
 
+## Transformers で Nano を試す
+
+中国語・英語・日本語の文字起こしには [Transformers 5.17.0 ガイド（英語）](./transformers_native.md) と公式 `FunAudioLLM/Fun-ASR-Nano-2512-hf` checkpoint を使えます。CPU サンプルがあり、toolkit とサービスの経路は別です。ネイティブ出力はテキストで、タイムスタンプ・話者・HTTP サーバーを追加しません。
+
 初めて FunASR を試すとき、Whisper やクラウド ASR から移行するとき、または OpenAI 互換 API で公開するモデル alias を決めるときに使ってください。
 
 ## 迷ったらここから

docs/model_selection_ko.md

@@ -1,5 +1,9 @@
 # FunASR 모델 선택 가이드
 
+## Transformers로 Nano 시작하기
+
+중국어·영어·일본어 전사는 [Transformers 5.17.0 가이드(영문)](./transformers_native.md)와 공식 `FunAudioLLM/Fun-ASR-Nano-2512-hf` checkpoint로 시작할 수 있습니다. CPU 예제가 있으며 toolkit과 서비스 경로는 별도입니다. 네이티브 출력은 텍스트이며 타임스탬프·화자·HTTP 서버를 추가하지 않습니다.
+
 처음 FunASR을 사용할 때, Whisper나 클라우드 ASR에서 전환할 때, 또는 OpenAI 호환 API에서 노출할 model alias를 정할 때 참고하세요.
 
 ## 고민된다면 여기서 시작

docs/model_selection_zh.md

@@ -1,5 +1,9 @@
 # FunASR 模型选择指南
 
+## 先用 Transformers 体验 Nano
+
+通过 Hugging Face API 转写中、英、日语音，先用 [原生 Transformers 5.17.0](./transformers_native_zh.md)、官方 `FunAudioLLM/Fun-ASR-Nano-2512-hf` 权重和 CPU 示例。下文的工具库与服务路径仍独立；原生导出不自动提供时间戳、说话人或 HTTP 接口。
+
 当你第一次选择模型、评估是否从 Whisper 或云端 ASR 迁移，或者准备通过 OpenAI 兼容 API 暴露模型别名时，可以先看这份指南。
 
 ## 默认快速路径

docs/python_api.md

@@ -1,5 +1,7 @@
 # Python SDK: AutoModel
 
+> **Only need native Fun-ASR-Nano transcription?** Start with [Transformers 5.17.0](./transformers_native.md). It loads the separate `-hf` checkpoint without the FunASR toolkit. This page covers the `funasr.AutoModel` toolkit path; do not mix dependencies, parameters or output contracts.
+
 [简体中文](python_api_zh.md) | [Installation](installation/installation.md) | [Model selection](model_selection.md)
 
 `from funasr import AutoModel` runs models inside your Python process. It is not an HTTP client and does not implement the entire OpenAI API. This guide describes the implementation in this checkout, not every historical FunASR release or upstream checkpoint.

docs/python_api_zh.md

@@ -1,5 +1,7 @@
 # Python SDK：AutoModel
 
+> **只需 Fun-ASR-Nano 原生推理？** 使用 [Transformers 5.17.0 快速开始](./transformers_native_zh.md)。它加载独立的 `-hf` 权重，不要求 FunASR 工具库。本页保留 `funasr.AutoModel` 工具库路径，两者的依赖、参数和输出不可混用。
+
 [English](python_api.md) | [安装](installation/installation_zh.md) | [模型选择](model_selection_zh.md)
 
 `from funasr import AutoModel` 在当前 Python 进程内运行模型。它不是 HTTP 客户端，也不实现完整的 OpenAI API。本文说明当前代码版本的实现，不代表所有历史 FunASR 版本或上游 checkpoint 的行为。