Skip to content

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

release: prepare 1.4.13

LauraGPTf2332313ac06
diff --git a/README.md b/README.md
index 847fe0aba..c53bbc433 100644
--- a/README.md
+++ b/README.md
@@ -338,7 +338,7 @@ inference on physical Blackwell hardware.
## 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 1.4.12** stabilizes Fun-ASR-Nano vLLM decoding when audio compute uses FP16: the Qwen3 decoder uses BF16, while GPUs without BF16 can select FP32. Install with `python -m pip install -U "funasr==1.4.12"`. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.12)
+- **FunASR 1.4.13** pins the core NumPy dependency below 2 to prevent binary ABI import failures. Install with `python -m pip install -U "funasr==1.4.13"`. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.13)
- **Production deployment** now includes faster, more resilient realtime serving and verified llama.cpp archives for ten Linux, macOS, and Windows targets. [GPU services ->](./docs/vllm_guide.md) · [CPU/edge packages ->](https://www.funasr.com/en/deploy/llama-cpp.html)
> 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.md
index af45a46d6..64f61f545 100644
--- a/README_ja.md
+++ b/README_ja.md
@@ -100,7 +100,7 @@ Whisper は単一モデルですが、**FunASR はツールキット**です—
## 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 1.4.12** は、audio compute が FP16 のときの Fun-ASR-Nano vLLM 出力を安定化します。Qwen3 decoder は BF16 を使い、BF16 非対応 GPU では FP32 を選択できます。`python -m pip install -U "funasr==1.4.12"`。[Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.12)
+- **FunASR 1.4.13** は、バイナリ ABI の import 失敗を避けるため、core NumPy 依存を 2 未満に固定します。`python -m pip install -U "funasr==1.4.13"`。[Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.13)
- **Production deployment** に、より高速で安定した realtime serving と、Linux、macOS、Windows の 10 target 向け llama.cpp package を追加しました。[GPU service ->](./docs/vllm_guide.md) · [CPU / edge package ->](https://www.funasr.com/en/deploy/llama-cpp.html) · [v0.2.6 binaries ->](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.6)
> 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.md
index 8b7467769..72fcf190b 100644
--- a/README_ko.md
+++ b/README_ko.md
@@ -100,7 +100,7 @@ Whisper는 단일 모델이지만, **FunASR는 툴킷**입니다. 용도에 맞
## 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 1.4.12**는 audio compute가 FP16일 때 Fun-ASR-Nano vLLM 출력을 안정화합니다. Qwen3 decoder는 BF16을 사용하며 BF16 미지원 GPU에서는 FP32를 선택할 수 있습니다. `python -m pip install -U "funasr==1.4.12"`. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.12)
+- **FunASR 1.4.13**은 바이너리 ABI import 실패를 막기 위해 core NumPy 의존성을 2 미만으로 고정합니다. `python -m pip install -U "funasr==1.4.13"`. [Release ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.13)
- **Production deployment**에 더 빠르고 안정적인 realtime serving과 Linux, macOS, Windows 10개 target용 llama.cpp package를 추가했습니다. [GPU service ->](./docs/vllm_guide.md) · [CPU / edge package ->](https://www.funasr.com/en/deploy/llama-cpp.html) · [v0.2.6 binaries ->](https://github.com/modelscope/FunASR/releases/tag/runtime-llamacpp-v0.2.6)
> 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.md
index 8253d6634..2aeebdfa5 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -150,7 +150,7 @@ Whisper 是单个模型,**FunASR 是一个工具箱**——按场景挑模型
## 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 1.4.12** 修复 Fun-ASR-Nano 使用 FP16 音频计算时的 vLLM 异常输出:Qwen3 解码器改用 BF16,不支持 BF16 的 GPU 可显式选择 FP32。升级命令:`python -m pip install -U "funasr==1.4.12"`。[发布页 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.12)
+- **FunASR 1.4.13** 将核心 NumPy 依赖限定在 2 以下,避免二进制 ABI 导入失败。升级命令:`python -m pip install -U "funasr==1.4.13"`。[发布页 ->](https://github.com/modelscope/FunASR/releases/tag/v1.4.13)
- **工业部署** 新增更快、更稳定的实时服务,以及覆盖 Linux、macOS、Windows 十种目标的 llama.cpp 预编译包。[GPU 服务 ->](./docs/vllm_guide_zh.md) · [CPU/端侧包 ->](https://www.funasr.com/deploy/llama-cpp.html)
> 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/funasr/version.txt b/funasr/version.txt
index f86e02988..acd81d7f2 100644
--- a/funasr/version.txt
+++ b/funasr/version.txt
@@ -1 +1 @@
-1.4.12
+1.4.13
diff --git a/tests/test_release_version_contract.py b/tests/test_release_version_contract.py
index 4e9c490b5..852203358 100644
--- a/tests/test_release_version_contract.py
+++ b/tests/test_release_version_contract.py
@@ -2,7 +2,7 @@ from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
-RELEASE_VERSION = "1.4.12"
+RELEASE_VERSION = "1.4.13"
README_FILES = ("README.md", "README_zh.md", "README_ja.md", "README_ko.md")