Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
docs(release): finalize 1.4.17 release documentation
zhifu gao42be336f83f8
diff --git a/README.md b/README.mdindex de182b59e..c28ea1606 100644--- a/README.md+++ b/README.md@@ -364,8 +364,8 @@ recordings with the same evaluation scope.## What's new- **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 1.4.17 release candidate** adds explicit PCM16 input and improves timestamp, hotword, speaker-sample-rate, and long-segment streaming handling. After publication, install with `python -m pip install -U "funasr==1.4.17"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)- **FunASR 1.4.16** remains the current published version. It preserves explicit VAD, punctuation, and speaker-model device placement across inference calls, and adds tested native Transformers adoption guides. Install with `python -m pip install -U "funasr==1.4.16"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)+- **FunASR 1.4.17** adds explicit PCM16 input and improves timestamp, hotword, speaker-sample-rate, and long-segment streaming handling. Install with `python -m pip install -U "funasr==1.4.17"`. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)+ **Previous release: FunASR 1.4.16** preserves explicit VAD, punctuation, and speaker-model device placement across inference calls, and adds tested native Transformers adoption guides. [Release and verification scope ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)- **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.diff --git a/README_ja.md b/README_ja.mdindex 96f3fa840..f4421ea66 100644--- a/README_ja.md+++ b/README_ja.md@@ -112,8 +112,8 @@ 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## 最新情報- **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 1.4.17 リリース候補**は明示的な PCM16 入力を追加し、timestamp、hotword、speaker sample rate、長い segment の streaming 処理を改善します。正式公開後に `python -m pip install -U "funasr==1.4.17"` でインストールできます。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)- 現在の正式版 **FunASR 1.4.16** は複数回の推論でも VAD、句読点、話者モデルの明示的な device 配置を保持し、テスト済みのネイティブ Transformers 導入ガイドを追加します。`python -m pip install -U "funasr==1.4.16"`。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)+- **FunASR 1.4.17** は明示的な PCM16 入力を追加し、timestamp、hotword、speaker sample rate、長い segment の streaming 処理を改善します。`python -m pip install -U "funasr==1.4.17"` でインストールできます。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)+ 前のリリース **FunASR 1.4.16** は複数回の推論でも VAD、句読点、話者モデルの明示的な device 配置を保持し、テスト済みのネイティブ Transformers 導入ガイドを追加しました。[リリースと検証範囲 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)- **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。diff --git a/README_ko.md b/README_ko.mdindex 28bfde059..d73df23f8 100644--- a/README_ko.md+++ b/README_ko.md@@ -111,8 +111,8 @@ checkpoint/revision, 오디오 집합, 하드웨어, 배치, 워밍업, 측정## 최신 소식- **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 1.4.17 릴리스 후보**는 명시적 PCM16 입력을 추가하고 timestamp, hotword, speaker sample rate, 긴 segment의 streaming 처리를 개선합니다. 정식 공개 후 `python -m pip install -U "funasr==1.4.17"`로 설치할 수 있습니다. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)- 현재 정식 버전인 **FunASR 1.4.16**은 여러 번의 추론에서도 VAD, 문장 부호, 화자 모델의 명시적 device 배치를 유지하고 검증된 네이티브 Transformers 도입 가이드를 추가합니다. `python -m pip install -U "funasr==1.4.16"`. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)+- **FunASR 1.4.17**은 명시적 PCM16 입력을 추가하고 timestamp, hotword, speaker sample rate, 긴 segment의 streaming 처리를 개선합니다. `python -m pip install -U "funasr==1.4.17"`로 설치할 수 있습니다. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)+ 이전 릴리스 **FunASR 1.4.16**은 여러 번의 추론에서도 VAD, 문장 부호, 화자 모델의 명시적 device 배치를 유지하고 검증된 네이티브 Transformers 도입 가이드를 추가했습니다. [릴리스 및 검증 범위 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)- **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.diff --git a/README_zh.md b/README_zh.mdindex 18c0cfd58..950dcc78b 100644--- a/README_zh.md+++ b/README_zh.md@@ -157,8 +157,8 @@ checkpoint/revision、音频集、硬件、批量大小、预热、计时范围## 最新动态- **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 1.4.17 发布候选**新增显式 PCM16 输入,改进时间戳、热词、说话人采样率与长片段流式处理。正式发布后安装:`python -m pip install -U "funasr==1.4.17"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)- **FunASR 1.4.16** 仍是当前正式版本,修复 VAD、标点和说话人子模型在多次推理时的显式设备放置,并新增经过测试的原生 Transformers 使用指南。升级命令:`python -m pip install -U "funasr==1.4.16"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)+- **FunASR 1.4.17** 新增显式 PCM16 输入,改进时间戳、热词、说话人采样率与长片段流式处理。安装:`python -m pip install -U "funasr==1.4.17"`。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)+ **上一版本:FunASR 1.4.16** 修复 VAD、标点和说话人子模型在多次推理时的显式设备放置,并新增经过测试的原生 Transformers 使用指南。[发布说明与验证范围 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)- **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)。diff --git a/docs/repository_roles.md b/docs/repository_roles.mdindex 55a469fae..071c3f4ed 100644--- a/docs/repository_roles.md+++ b/docs/repository_roles.md@@ -5,9 +5,7 @@ This document explains the responsibility boundaries, user entry points, and iss> **Directional roadmap, not a release promise.**> This document records shipped capabilities and active work, but does not commit to> future version numbers or dates. The current Python release is-> [`funasr==1.4.16`](https://github.com/modelscope/FunASR/releases/tag/v1.4.16).-> The prepared release candidate is-> [`funasr==1.4.17`](https://github.com/modelscope/FunASR/releases/tag/v1.4.17); it is not published yet.+> [`funasr==1.4.17`](https://github.com/modelscope/FunASR/releases/tag/v1.4.17).> Any future breaking release still requires a maintainer-approved milestone and> migration plan.diff --git a/docs/repository_roles_zh.md b/docs/repository_roles_zh.mdindex f28bd61fd..96d6abd07 100644--- a/docs/repository_roles_zh.md+++ b/docs/repository_roles_zh.md@@ -4,8 +4,7 @@> **方向性路线图,不是版本承诺。**> 本文档记录已交付能力与正在推进的工作,但不承诺未来版本号或日期。当前 Python-> 版本是 [`funasr==1.4.16`](https://github.com/modelscope/FunASR/releases/tag/v1.4.16)。-> 已准备的发布候选是 [`funasr==1.4.17`](https://github.com/modelscope/FunASR/releases/tag/v1.4.17),目前尚未正式发布。+> 版本是 [`funasr==1.4.17`](https://github.com/modelscope/FunASR/releases/tag/v1.4.17)。> 任何未来的 breaking release 仍需 maintainer 确认 milestone 与迁移方案。---diff --git a/tests/test_release_version_contract.py b/tests/test_release_version_contract.pyindex 2ae5d1bce..247165b66 100644--- a/tests/test_release_version_contract.py+++ b/tests/test_release_version_contract.py@@ -29,5 +29,23 @@ def test_repository_role_guides_link_the_current_release():for name in REPOSITORY_ROLE_FILES:text = (ROOT / name).read_text(encoding="utf-8")+++def test_release_documents_do_not_describe_a_pending_candidate():+ candidate_labels = ("release candidate", "\u53d1\u5e03\u5019\u9009",+ "\u30ea\u30ea\u30fc\u30b9\u5019\u88dc", "\ub9b4\ub9ac\uc2a4 \ud6c4\ubcf4")+ for name in README_FILES:+ text = (ROOT / name).read_text(encoding="utf-8")+ version_lines = [line for line in text.splitlines() if RELEASE_VERSION in line]+ assert version_lines, name+ assert not any(label in line.lower() for line in version_lines+ for label in candidate_labels), name+ assert 'pip install -U "funasr==1.4.16"' not in text, name+ for name in REPOSITORY_ROLE_FILES:+ text = (ROOT / name).read_text(encoding="utf-8")+ assert "funasr==1.4.16" not in text, name+ assert "not published yet" not in text, name+ assert "\u5c1a\u672a\u6b63\u5f0f\u53d1\u5e03" not in text, name+ assert not any(label in text.lower() for label in candidate_labels), nameassert f"funasr=={RELEASE_VERSION}" in textassert f"releases/tag/v{RELEASE_VERSION}" in text