From 28a08f726cdc1e67336cb65faf06d4e69972ce43 Mon Sep 17 00:00:00 2001 From: wehub-resource-sync Date: Mon, 13 Jul 2026 10:36:36 +0000 Subject: [PATCH] docs: make Chinese README the default --- README.md | 301 ++++++++++++++++++++++++++---------------------------- 1 file changed, 146 insertions(+), 155 deletions(-) diff --git a/README.md b/README.md index 4f29f49..429a499 100644 --- a/README.md +++ b/README.md @@ -1,19 +1,25 @@ -([简体中文](./README_zh.md)|English|[日本語](./README_ja.md)|[한국어](./README_ko.md)) + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/modelscope/FunASR) · [上游 README](https://github.com/modelscope/FunASR/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 + +([English](./README.md)|简体中文|[日本語](./README_ja.md)|[한국어](./README_ko.md))

FunASR

- Industrial speech recognition. Up to 340x realtime, 26x faster than Whisper. 50+ languages.
- Speaker diarization · Emotion detection · Streaming · One API call + 工业级语音识别。最高 340 倍实时，比 Whisper 快 26 倍。支持 50+ 语言。
+ 说话人分离 · 情感识别 · 流式转写 · 一次调用搞定

PyPI Stars Downloads - Docs + Docs

@@ -21,60 +27,52 @@

- Quick Start · Colab · Benchmark · Model selection · Migration guide · Use cases · Deployment matrix · Models · Agent Integration · Docs · Contribute + 快速开始 · Colab · 性能评测 · 模型选择 · 迁移指南 · 场景速览 · 部署选型 · 模型列表 · Agent 集成 · 文档 · 贡献

--- -## Quick Start +## 快速开始 [![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. +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。 ```bash -pip install torch torchaudio pip install funasr ``` -**Flagship model — Fun-ASR-Nano** (LLM-ASR, 31 languages; the default recommendation, needs a GPU): - -```python -from funasr import AutoModel - -model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", device="cuda") -result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav") -print(result[0]["text"]) -# 欢迎大家来体验达摩院推出的语音识别模型。 -``` - -On CPU (or for multilingual + emotion in one pass), use **SenseVoice** — which also returns speaker diarization and timestamps: - ```python from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess -model = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda") # use device="cpu" if you don't have a GPU -result = model.generate( - input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", - batch_size_s=300, -) +model = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda") +result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav") -# One call returns VAD segments with speaker id + timestamps — render them however you like: +# 一次调用即返回带说话人 id 和时间戳的 VAD 分段，可自由渲染： for seg in result[0]["sentence_info"]: - print(f"[{seg['start']/1000:.1f}s] Speaker {seg['spk']}: {rich_transcription_postprocess(seg['sentence'])}") + print(f"[{seg['start']/1000:.1f}s] 说话人{seg['spk']}: {rich_transcription_postprocess(seg['sentence'])}") ``` -**Output** — structured text with speaker labels, timestamps, and punctuation: +**输出** — 带说话人标签、时间戳和标点的结构化文本： ``` -[0.6s] Speaker 0: 欢迎大家来体验达摩院推出的语音识别模型 +[0.6s] 说话人0: 欢迎大家来体验达摩院推出的语音识别模型 ``` -That's it. **One model, one call** — VAD segmentation, speech recognition, punctuation, speaker diarization all happen automatically. +一个模型、一次调用 — VAD 分段、语音识别、标点恢复、说话人分离全部自动完成。 -### Scale & deploy the flagship +### LLM 语音识别：Fun-ASR-Nano -At scale, accelerate Fun-ASR-Nano with vLLM (batch processing): +追求更高精度、支持 31 种语言（含中文方言），使用 [Fun-ASR-Nano](https://github.com/FunAudioLLM/Fun-ASR) — SenseVoice 编码器 + Qwen3-0.6B 解码器的 LLM-based ASR： + +```python +from funasr import AutoModel + +model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", vad_model="fsmn-vad", device="cuda") +result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav") +``` + +使用 vLLM 加速（批量处理快 16 倍）： ```python from funasr.auto.auto_model_vllm import AutoModelVLLM @@ -83,83 +81,127 @@ model = AutoModelVLLM(model="FunAudioLLM/Fun-ASR-Nano-2512", tensor_parallel_siz results = model.generate(["audio1.wav", "audio2.wav"], language="auto") ``` -> **Deploy as API server:** `funasr-server --device cuda` → OpenAI-compatible endpoint at localhost:8000 +> **部署为 API 服务：** `funasr-server --device cuda` → 本地 OpenAI 兼容接口 localhost:8000 > -> **Use with AI agents:** [MCP Server](examples/mcp_server/) for Claude/Cursor · [OpenAI API](examples/openai_api/) for LangChain/Dify/AutoGen +> **接入 AI Agent：** [MCP 服务](examples/mcp_server/) 支持 Claude/Cursor · [OpenAI API](examples/openai_api/README_zh.md) 支持 LangChain/Dify/AutoGen -### Why FunASR? +### 为什么选 FunASR？ -Whisper is a single model; **FunASR is a toolkit** — you pick the right model per job: **Fun-ASR-Nano** (flagship LLM-ASR, GPU, 340x realtime with vLLM, 31 languages), **SenseVoice** (CPU-friendly, + emotion & audio events), **Paraformer** (low-latency streaming). The table shows what the toolkit delivers vs one Whisper model — each capability is labelled with the model that provides it: +Whisper 是单个模型，**FunASR 是一个工具箱**——按场景挑模型：**Fun-ASR-Nano**（旗舰 LLM-ASR，需 GPU，vLLM 下 340 倍实时，31 种语言）、**SenseVoice**（CPU 友好，额外带情感与音频事件）、**Paraformer**（低延迟流式）。下表是工具箱相比单个 Whisper 模型能提供什么——每项能力都标注了由哪个模型提供： -| | FunASR (toolkit) | Whisper | Cloud APIs | +| | FunASR（工具箱） | Whisper | 云端 API | |---|---|---|---| -| Top speed | **340x realtime** (Fun-ASR-Nano + vLLM) | 13x realtime | ~1x realtime | -| Speaker ID | ✅ Built-in | ❌ Needs pyannote | ✅ Extra cost | -| Emotion | ✅ via SenseVoice | ❌ | ❌ | -| Languages | 50+ (Qwen3-ASR 52, Nano 31) | 57 | Varies | -| Streaming | ✅ WebSocket (Paraformer) | ❌ | ✅ | -| CPU viable | ✅ 17x realtime (SenseVoice) | ❌ Too slow | N/A | -| Self-hosted | ✅ MIT license | ✅ MIT license | ❌ Cloud only | -| Cost | Free | Free | $0.006/min+ | +| 最高速度 | **340 倍实时**（Fun-ASR-Nano + vLLM） | 13 倍实时 | ~1 倍实时 | +| 说话人识别 | ✅ 内置 | ❌ 需要 pyannote | ✅ 额外付费 | +| 情感识别 | ✅ 由 SenseVoice 提供 | ❌ | ❌ | +| 语言数 | 50+（Qwen3-ASR 52、Nano 31） | 57 | 因服务而异 | +| 流式识别 | ✅ WebSocket（Paraformer） | ❌ | ✅ | +| CPU 可用 | ✅ 17 倍实时（SenseVoice） | ❌ 太慢 | 不适用 | +| 私有部署 | ✅ MIT 开源 | ✅ MIT 开源 | ❌ 仅云端 | +| 费用 | 免费 | 免费 | ¥0.04/分钟起 | -Trying FunASR for the first time? Use the [Colab quickstart](./examples/colab/) before setting up a local environment. Choosing a first model? Start with the [model selection guide](./docs/model_selection.md). Planning a switch from Whisper or a cloud ASR provider? Use the [migration guide](./docs/migration_from_whisper.md) and [benchmark example](./examples/migration/) to test representative audio, map features, and roll out safely. +第一次试用 FunASR？可以先跑 [Colab 快速体验](./examples/colab/README_zh.md)，再配置本地环境。还不确定先用哪个模型？先看 [模型选择指南](./docs/model_selection_zh.md)。计划从 Whisper 或云端 ASR 切换？请按 [迁移指南](./docs/migration_from_whisper_zh.md) 和 [评测示例](./examples/migration/) 用代表性音频评测、映射功能并安全上线。 --- -## Installation + -```bash -pip install funasr -``` +## 性能评测 -
From source / Requirements +> 184 条长音频（共 192 分钟）。[完整报告 →](https://modelscope.github.io/FunASR/zh/benchmark.html) -```bash -git clone https://github.com/modelscope/FunASR.git && cd FunASR -pip install -e ./ -``` -Requirements: Python ≥ 3.8. Install PyTorch + torchaudio first ([pytorch.org](https://pytorch.org/get-started/locally/)), then `pip install funasr`. +| 模型 | 中文 CER ↓ | GPU 速度 | CPU 速度 | 对比 Whisper-large-v3 | +|------|------|----------|----------|---------------------| +| **Fun-ASR-Nano**（vLLM） | **8.20%** | **340 倍**实时 | — | 🚀 **快 26 倍** | +| **SenseVoice-Small** | **7.81%** | **170 倍**实时 | **17 倍**实时 | 🚀 **快 13 倍** | +| **Paraformer-Large** | 10.18% | **120 倍**实时 | **15 倍**实时 | 🚀 **快 9 倍** | +| Whisper-large-v3-turbo | 21.71% | 46 倍实时 | ❌ | 快 3.4 倍 | +| Whisper-large-v3 | 20.02% | 13 倍实时 | ❌ | 基准 | + +> **一句话：** FunASR 在 CPU 上的速度，比 Whisper 在 GPU 上还快。 + +--- + +## 最新动态 + +- 2026/05/24：**vLLM 推理引擎** — Fun-ASR-Nano 解码加速 2-3 倍。支持流式 WebSocket 服务（VAD + 说话人分离 + 热词）。[文档 →](docs/vllm_guide_zh.md) · [实时 WS 调优 →](docs/vllm_guide_zh.md#67-生产并发与多进程部署) · [API 稳定性清单 →](docs/vllm_guide_zh.md#生产-api-稳定性清单) +- 2026/05/24：**动态 VAD** — 自适应静音阈值（默认开启），短句不切碎、长句自动切分。[详情 →](docs/vllm_guide_zh.md#7-动态-vad) +- 2026/05/24：**v1.3.3** — `funasr-server` 命令行工具、OpenAI 兼容 API、MCP 服务。`pip install --upgrade funasr` +- 2026/05/20：新增 Qwen3-ASR (0.6B/1.7B)，52 种语言自动检测。[使用方法](examples/industrial_data_pretraining/qwen3_asr) +- 2026/05/20：新增 GLM-ASR-Nano (1.5B)，17 种语言，方言优化。[使用方法](examples/industrial_data_pretraining/glm_asr) +- 2026/05/19：Fun-ASR-Nano 和 SenseVoice 支持说话人分离。 +- 2025/12/15：[Fun-ASR-Nano-2512](https://github.com/FunAudioLLM/Fun-ASR) 上线。 + +
更早 + +- 2024/10/10：支持 Whisper-large-v3-turbo。 +- 2024/07/04：[SenseVoice](https://github.com/FunAudioLLM/SenseVoice) 发布。 +- 2024/01/30：FunASR 1.0 发布。
--- -## Model Zoo +## 安装 -| Model | Task | Languages | Params | Links | -|-------|------|-----------|--------|-------| -| **Fun-ASR-Nano** | ASR + timestamps | 31 languages | 800M | [⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512) | -| **SenseVoiceSmall** | ASR + emotion + events | zh/en/ja/ko/yue | 234M | [⭐](https://www.modelscope.cn/models/iic/SenseVoiceSmall) [🤗](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) | -| **Paraformer-zh** | ASR + timestamps | zh/en | 220M | [⭐](https://www.modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗](https://huggingface.co/funasr/paraformer-zh) | -| Paraformer-zh-streaming | Streaming ASR | zh/en | 220M | [⭐](https://modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗](https://huggingface.co/funasr/paraformer-zh-streaming) | -| Qwen3-ASR | ASR, 52 languages | multilingual | 1.7B | [usage](examples/industrial_data_pretraining/qwen3_asr) | -| GLM-ASR-Nano | ASR, 17 languages | multilingual | 1.5B | [usage](examples/industrial_data_pretraining/glm_asr) | -| Whisper-large-v3 | ASR + translation | multilingual | 1550M | [usage](examples/industrial_data_pretraining/whisper) | -| Whisper-large-v3-turbo | ASR + translation | multilingual | 809M | [usage](examples/industrial_data_pretraining/whisper) | -| ct-punc | Punctuation | zh/en | 290M | [⭐](https://modelscope.cn/models/iic/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗](https://huggingface.co/funasr/ct-punc) | -| fsmn-vad | VAD | zh/en | 0.4M | [⭐](https://modelscope.cn/models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗](https://huggingface.co/funasr/fsmn-vad) | -| cam++ | Speaker diarization | — | 7.2M | [⭐](https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [🤗](https://huggingface.co/funasr/campplus) | -| emotion2vec+large | Emotion recognition | — | 300M | [⭐](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary) [🤗](https://huggingface.co/emotion2vec/emotion2vec_plus_large) | +```bash +pip install funasr +``` + +
从源码安装 + +```bash +git clone https://github.com/modelscope/FunASR.git && cd FunASR +pip install -e ./ +``` +环境要求：Python ≥ 3.8、PyTorch ≥ 1.13、torchaudio + +
--- -## Usage + -> Full examples with parameter docs: [Tutorial →](https://modelscope.github.io/FunASR/tutorial.html) +## 模型列表 + +| 模型 | 任务 | 语言 | 参数量 | 链接 | +|------|------|------|--------|------| +| **Fun-ASR-Nano** | 识别 + 时间戳 | 31 种语言 | 800M | [⭐](https://www.modelscope.cn/models/FunAudioLLM/Fun-ASR-Nano-2512) [🤗](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512) | +| **SenseVoiceSmall** | 识别 + 情感 + 事件 | 中/英/日/韩/粤 | 234M | [⭐](https://www.modelscope.cn/models/iic/SenseVoiceSmall) [🤗](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) | +| **Paraformer-zh** | 识别 + 时间戳 | 中/英 | 220M | [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [🤗](https://huggingface.co/funasr/paraformer-zh) | +| Paraformer-zh-streaming | 流式识别 | 中/英 | 220M | [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗](https://huggingface.co/funasr/paraformer-zh-streaming) | +| Qwen3-ASR | 识别，52 种语言 | 多语言 | 1.7B | [使用](examples/industrial_data_pretraining/qwen3_asr) | +| GLM-ASR-Nano | 识别，17 种语言 | 多语言 | 1.5B | [使用](examples/industrial_data_pretraining/glm_asr) | +| Whisper-large-v3 | 识别 + 翻译 | 多语言 | 1550M | [使用](examples/industrial_data_pretraining/whisper) | +| Whisper-large-v3-turbo | 识别 + 翻译 | 多语言 | 809M | [使用](examples/industrial_data_pretraining/whisper) | +| ct-punc | 标点恢复 | 中/英 | 290M | [⭐](https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [🤗](https://huggingface.co/funasr/ct-punc) | +| fsmn-vad | 语音检测 | 中/英 | 0.4M | [⭐](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [🤗](https://huggingface.co/funasr/fsmn-vad) | +| cam++ | 说话人分离 | — | 7.2M | [⭐](https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [🤗](https://huggingface.co/funasr/campplus) | +| emotion2vec+large | 情感识别 | — | 300M | [⭐](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary) [🤗](https://huggingface.co/emotion2vec/emotion2vec_plus_large) | + +--- + +## 使用示例 + +> 完整参数文档：[教程 →](https://modelscope.github.io/FunASR/zh/tutorial.html) ```python from funasr import AutoModel -# Chinese production (VAD + ASR + punctuation + speaker) +# 中文生产级（VAD + 识别 + 标点 + 说话人） model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", spk_model="cam++", device="cuda") result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", hotword="关键词 20") +# 31 种语言 + 时间戳 +model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", hub="hf", trust_remote_code=True, + vad_model="fsmn-vad", vad_kwargs={"max_single_segment_time": 30000}, device="cuda") +result = model.generate(input="audio.wav", batch_size=1) -# Streaming real-time (feed audio chunk by chunk) +# 流式实时识别(逐块喂音频) import soundfile as sf model = AutoModel(model="paraformer-zh-streaming", device="cuda") -audio, sr = sf.read("speech.wav", dtype="float32") # 16 kHz mono -chunk_size = [0, 10, 5] # 600 ms chunks +audio, sr = sf.read("speech.wav", dtype="float32") # 16 kHz 单声道 +chunk_size = [0, 10, 5] # 每块 600ms chunk_stride = chunk_size[1] * 960 cache = {} n_chunks = (len(audio) - 1) // chunk_stride + 1 @@ -170,49 +212,48 @@ for i in range(n_chunks): if res[0]["text"]: print(res[0]["text"], end="", flush=True) -# Emotion recognition +# 情感识别 model = AutoModel(model="emotion2vec_plus_large", device="cuda") result = model.generate(input="audio.wav", granularity="utterance") ``` - -### CLI (Agent-Friendly) +### 命令行工具（Agent 友好） ```bash -# Transcribe audio (simplest) +# 转写音频（最简用法） funasr audio.wav -# JSON output (for AI agents) +# JSON 输出（适合 AI Agent 调用） funasr audio.wav --output-format json -# SRT subtitles +# 生成 SRT 字幕 funasr audio.wav --output-format srt --output-dir ./subs -# Speaker diarization + timestamps +# 说话人分离 + 时间戳 funasr audio.wav --spk --timestamps -f json -# Choose model and language +# 指定模型和语言 funasr audio.wav --model paraformer --language zh -# Batch transcribe +# 批量转写 funasr *.wav --output-format srt --output-dir ./output ``` -Available models: `sensevoice` (default), `paraformer`, `paraformer-en`, `fun-asr-nano` +可用模型：`sensevoice`（默认）、`paraformer`、`paraformer-en`、`fun-asr-nano` + --- -## Deploy +## 部署 ```bash -# OpenAI-compatible API (recommended) -pip install torch torchaudio -pip install funasr vllm fastapi uvicorn python-multipart -funasr-server --device cuda -# → POST /v1/audio/transcriptions at localhost:8000 +# OpenAI 兼容 API（推荐） +pip install funasr fastapi uvicorn python-multipart +funasr-server --model sensevoice --device cuda +# → POST /v1/audio/transcriptions，地址 localhost:8000 ``` -Verify it with a public sample: +使用公开样例音频验证服务： ```bash curl -L https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav -o sample.wav @@ -223,75 +264,25 @@ curl http://localhost:8000/v1/audio/transcriptions \ ``` ```bash -# Docker streaming service +# Docker 流式服务 docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12 ``` -### CPU / Edge — llama.cpp / GGUF (no GPU, no Python) +> **CPU / 边缘部署(无需 GPU、无需 Python):** 用 **llama.cpp / GGUF** 跑 Fun-ASR-Nano / SenseVoice / Paraformer —— 单个自包含二进制,对标 whisper.cpp。详见 [runtime/llama.cpp/](./runtime/llama.cpp/)。 -Run **SenseVoice / Paraformer / Fun-ASR-Nano** as a **single self-contained binary** on CPU and edge devices — this is to FunASR what [whisper.cpp](https://github.com/ggml-org/whisper.cpp) is to Whisper, but with **~3× lower CER than whisper.cpp on Chinese**. Built-in FSMN-VAD, no Python at runtime. - -```bash -# 1) Grab a prebuilt binary from Releases (Linux / macOS / Windows), then: -bash download-funasr-model.sh sensevoice ./gguf # or: paraformer | nano -llama-funasr-sensevoice -m ./gguf/SenseVoiceSmall-f16.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav -# → 欢迎大家来体验达摩院推出的语音识别模型 -``` - -**Prebuilt binaries:** [Releases](../../releases) · **Download & quickstart:** [funasr.com/llama-cpp](https://www.funasr.com/llama-cpp.html) · **GGUF models:** [Hugging Face](https://huggingface.co/FunAudioLLM) · **Docs & benchmarks:** [runtime/llama.cpp/](./runtime/llama.cpp/) - -[OpenAI API example →](./examples/openai_api/) · [Gradio demo →](./examples/openai_api/GRADIO.md) · [Client recipes →](./examples/openai_api/CLIENTS.md) · [JavaScript/TypeScript recipes →](./examples/openai_api/JAVASCRIPT.md) · [Kubernetes template →](./examples/openai_api/kubernetes/) · [Workflow recipes →](./examples/openai_api/WORKFLOWS.md) · [Postman collection →](./examples/openai_api/POSTMAN.md) · [OpenAPI spec →](./examples/openai_api/OPENAPI.md) · [Security guide →](./examples/openai_api/SECURITY.md) · [Deployment matrix →](./docs/deployment_matrix.md) · [Deployment docs →](./runtime/readme.md) · [Agent integration →](https://modelscope.github.io/FunASR/agent.html) +[OpenAI API 示例 →](./examples/openai_api/README_zh.md) · [Gradio Demo →](./examples/openai_api/GRADIO_zh.md) · [客户端配方 →](./examples/openai_api/CLIENTS.md) · [JavaScript/TypeScript 配方 →](./examples/openai_api/JAVASCRIPT_zh.md) · [Kubernetes 模板 →](./examples/openai_api/kubernetes/README_zh.md) · [工作流配方 →](./examples/openai_api/WORKFLOWS_zh.md) · [Postman 集合 →](./examples/openai_api/POSTMAN_zh.md) · [OpenAPI 规范 →](./examples/openai_api/OPENAPI_zh.md) · [安全指南 →](./examples/openai_api/SECURITY_zh.md) · [部署选型 →](./docs/deployment_matrix_zh.md) · [部署文档 →](./runtime/readme_cn.md) · [Agent 集成 →](https://modelscope.github.io/FunASR/agent.html) --- -## Benchmark - -> 184 long-form audio files (192 min). [Full report →](https://modelscope.github.io/FunASR/benchmark.html) · [RTFx and reproducibility notes →](./docs/benchmark/rtf_reproducibility.md) - -| Model | Chinese CER ↓ | GPU Speed | CPU Speed | vs Whisper-large-v3 | -|-------|------|-----------|-----------|-------------------| -| **Fun-ASR-Nano** (vLLM) | **8.20%** | **340x** realtime | — | 🚀 **26x faster** | -| **SenseVoice-Small** | **7.81%** | **170x** realtime | **17x** realtime | 🚀 **13x faster** | -| **Paraformer-Large** | 10.18% | **120x** realtime | **15x** realtime | 🚀 **9x faster** | -| Whisper-large-v3-turbo | 21.71% | 46x realtime | ❌ | 3.4x faster | -| Whisper-large-v3 | 20.02% | 13x realtime | ❌ | baseline | - -> **Key takeaway:** FunASR models run on CPU faster than Whisper runs on GPU. - ---- - -## What's new - -- 2026/06/20: **llama.cpp / GGUF runtime** — run SenseVoice / Paraformer / Fun-ASR-Nano on CPU & edge as a single self-contained binary (a whisper.cpp-style alternative), built-in FSMN-VAD, no Python at runtime. Prebuilt binaries for Linux / macOS / Windows + **q8 quantized models (~half the size, same accuracy)**. [runtime/llama.cpp/](./runtime/llama.cpp/) · [Releases](../../releases) -- 2026/06/21: **v1.3.12** on PyPI — rolling fixes (qwen3-asr language codes, glm_asr, vLLM repetition_penalty). `pip install --upgrade funasr` -- 2026/05/24: **vLLM Inference Engine** — 2-3x faster LLM decoding for Fun-ASR-Nano. Streaming WebSocket service with VAD + Speaker Diarization. [Guide →](docs/vllm_guide.md) · [Realtime WS tuning →](docs/vllm_guide.md#67-production-concurrency-and-multi-process-deployment) · [API stability checklist →](docs/vllm_guide.md#production-api-stability-checklist) -- 2026/05/24: **Dynamic VAD** — adaptive silence threshold (default on). Short sentences stay intact, long segments get auto-split. [Details →](docs/vllm_guide.md#附录dynamicstreamingvad) -- 2026/05/24: **v1.3.3** — `funasr-server` CLI, OpenAI-compatible API, MCP Server for AI agents. `pip install --upgrade funasr` -- 2026/05/20: Added Qwen3-ASR (0.6B/1.7B) — 52 languages, auto detection. [usage](examples/industrial_data_pretraining/qwen3_asr) -- 2026/05/20: Added GLM-ASR-Nano (1.5B) — 17 languages, dialect support. [usage](examples/industrial_data_pretraining/glm_asr) -- 2026/05/19: Fun-ASR-Nano and SenseVoice now support speaker diarization. -- 2025/12/15: [Fun-ASR-Nano-2512](https://github.com/FunAudioLLM/Fun-ASR) — 31 languages, tens of millions of hours training. - -
Older - -- 2024/10/10: Whisper-large-v3-turbo support added. -- 2024/07/04: [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) — ASR + emotion + audio events. -- 2024/01/30: FunASR 1.0 released. - -
- ---- - -## Community +## 社区 | | | |---|---| -| 📖 [Documentation](https://modelscope.github.io/FunASR/) | 🐛 [Issues](https://github.com/modelscope/FunASR/issues) | -| 💬 [Discussions](https://github.com/modelscope/FunASR/discussions) | 🤗 [HuggingFace](https://huggingface.co/funasr) | -| 🤝 [Contributing](./CONTRIBUTING.md) | 🌐 [funasr.com](https://www.funasr.com) | -| 🧩 [Community projects](./docs/community_projects.md) | 💡 [Use-case showcase](./docs/use_case_showcase.md) | +| 📖 [文档](https://modelscope.github.io/FunASR/zh/) | 🐛 [问题反馈](https://github.com/modelscope/FunASR/issues) | +| 💬 [讨论](https://github.com/modelscope/FunASR/discussions) | 🤗 [HuggingFace](https://huggingface.co/funasr) | +| 🤝 [贡献指南](./CONTRIBUTING.md) | 📈 [20k 增长计划](./docs/community_growth_20k.md) | -## Star History +## Star 趋势 @@ -301,11 +292,11 @@ llama-funasr-sensevoice -m ./gguf/SenseVoiceSmall-f16.gguf --vad ./gguf/fsmn-vad -## License +## 许可证 [MIT License](./LICENSE) -## Citations +## 引用 ```bibtex @inproceedings{gao2023funasr,