Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -283,6 +283,7 @@ hf download FunAudioLLM/fsmn-vad-GGUF fsmn-vad.gguf --local-dir .\gguf

## What's new

- 2026/07/18: **v1.3.16 on PyPI** — client-driven realtime endpoints for Fun-ASR-Nano. Start one WebSocket session, stream PCM, and send `COMMIT` for each utterance without loading server-side VAD; short utterances finalize and timestamps remain monotonic across commits. Install with `pip install --upgrade funasr`, then run `funasr-realtime-server --endpoint-mode client`. [Guide →](examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md)
- 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)
Expand Down
1 change: 1 addition & 0 deletions README_zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,7 @@ Whisper 是单个模型,**FunASR 是一个工具箱**——按场景挑模型

## 最新动态

- 2026/07/18:**v1.3.16 已发布到 PyPI** — Fun-ASR-Nano 实时服务新增客户端分句模式。一个 WebSocket 会话可连续发送 PCM,并用 `COMMIT` 提交每个句子;无需加载服务端 VAD,短句可正常结束,多轮时间戳保持递增。执行 `pip install --upgrade funasr` 后,可用 `funasr-realtime-server --endpoint-mode client` 启动。[使用文档 →](examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md)
- 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`
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,13 @@ pip install -r requirements.txt
CUDA_VISIBLE_DEVICES=0 python serve_realtime_ws.py --port 10095 --language 中文
```

从 PyPI 安装时无需进入仓库目录;按主文档安装匹配的 vLLM 后,直接运行:

```bash
pip install --upgrade funasr
CUDA_VISIBLE_DEVICES=0 funasr-realtime-server --port 10095 --language 中文
```

### 客户端 VAD / 低延迟对话模式

客户端已经持续执行 VAD 时,可以关闭服务端 VAD 模型,并由客户端明确提交每句话:
Expand All @@ -24,6 +31,8 @@ CUDA_VISIBLE_DEVICES=0 python serve_realtime_ws.py \
--port 10095 --language 中文 --endpoint-mode client
```

PyPI 安装对应的命令为 `funasr-realtime-server --endpoint-mode client`。

同一条 WebSocket 连接上的协议为:

1. 发送文本 `START`;
Expand Down Expand Up @@ -70,7 +79,7 @@ ssh -L 10095:localhost:10095 <server>

| 文件 | 说明 |
|------|------|
| `serve_realtime_ws.py` | WebSocket 服务端 |
| `serve_realtime_ws.py` | 仓库兼容入口,调用 PyPI 包内的 WebSocket 服务端 |
| `client_mic.html` | 浏览器客户端 |
| `client_python.py` | Python CLI 客户端 |
| `client_test.py` | 自动化测试脚本 |
Expand Down
Loading
Loading