热门搜索:
quantatrisk/funasr-api
quantatrisk
基于FunASR和Qwen3-ASR的生产级本地语音识别API服务，支持多模型、OpenAI API兼容接口、流式识别和说话人分离，提供GPU加速和批量处理能力。
下载次数: 0状态：社区镜像维护者：quantatrisk仓库类型：镜像最近更新：1 个月前
让 AI 帮你使用轩辕镜像？ · 展开查看说明
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具，协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题，请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可：
请先完整阅读并严格遵守以下文档中的全部规则与要求：
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前，不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式，不推荐豆包 AI；Cursor 等编辑器可在对话 @ 该链接，或加入 User Rules。 若 AI 无法访问外链，可 打开说明文档 复制全文粘贴。文档会随站点更新，复制内容可能过期，建议定期检查。
FunASR-API
Production-ready local speech recognition API service powered by https://github.com/alibaba-damo-academy/FunASR and https://github.com/QwenLM/Qwen3-ASR.
Quick Start
GPU Version (Recommended)
bashdocker run -d --name funasr-api \ --gpus all \ -p 17003:8000 \ -e ENABLED_MODELS=auto \ -e API_KEY=your_api_key \ -v ./models/modelscope:/root/.cache/modelscope \ -v ./models/huggingface:/root/.cache/huggingface \ -v ./logs:/app/logs \ -v ./temp:/app/temp \ quantatrisk/funasr-api:gpu-latest
CPU Version
bashdocker run -d --name funasr-api \ -p 17003:8000 \ -e ENABLED_MODELS=paraformer-large \ -e API_KEY=your_api_key \ -v ./models/modelscope:/root/.cache/modelscope \ -v ./logs:/app/logs \ -v ./temp:/app/temp \ quantatrisk/funasr-api:cpu-latest
Supported Tags
| Tag | Description |
|---|---|
gpu-latest | GPU version with CUDA 12.6, auto model selection |
cpu-latest | CPU-only version, Paraformer model only |
Features
- Multi-Model Support: Qwen3-ASR (1.7B/0.6B) + Paraformer Large
- OpenAI API Compatible:
/v1/audio/transcriptionsendpoint - Alibaba Cloud Compatible: RESTful and WebSocket streaming API
- Speaker Diarization: Automatic multi-speaker identification
- Word-Level Timestamps: Qwen3-ASR supports precise timestamps
- Smart Far-Field Filtering: Reduces ambient noise in streaming
- GPU Batch Processing: 2-3x faster with batch inference
Environment Variables
| Variable | Default | Description |
|---|---|---|
ENABLED_MODELS | auto | Models to load: auto, all, or comma-separated list |
API_KEY | - | API authentication key (optional) |
LOG_LEVEL | INFO | Log level: DEBUG, INFO, WARNING, ERROR |
MAX_AUDIO_SIZE | 2048 | Max audio file size in MB |
ASR_BATCH_SIZE | 4 | Batch size for inference (GPU: 4, CPU: 2) |
MAX_SEGMENT_SEC | 90 | Max audio segment duration in seconds |
DEVICE | auto | Device: auto, cpu, cuda:0 |
Auto Mode Behavior
- VRAM >= 32GB: Auto-load
qwen3-asr-1.7b+paraformer-large - VRAM < 32GB: Auto-load
qwen3-asr-0.6b+paraformer-large - No CUDA: Only
paraformer-large(Qwen3 requires GPU)
API Endpoints
- OpenAI Compatible:
POST /v1/audio/transcriptions - Alibaba Cloud:
POST /stream/v1/asr - WebSocket:
/ws/v1/asr,/ws/v1/asr/qwen - Health Check:
GET /stream/v1/asr/health - API Docs:
http://localhost:17003/docs
Quick Test
bash# Health check curl http://localhost:17003/stream/v1/asr/health # Transcription with OpenAI API curl -X POST "http://localhost:17003/v1/audio/transcriptions" \ -H "Authorization: Bearer your_api_key" \ -F "file=@audio.wav" \ -F "model=qwen3-asr-1.7b" \ -F "response_format=verbose_json" # Transcription with Alibaba Cloud API curl -X POST "http://localhost:17003/stream/v1/asr" \ -H "Content-Type: application/octet-stream" \ --data-binary @audio.wav
Model Storage
Models are cached in Docker volumes for offline use:
bash# ModelScope models (Paraformer, VAD, CAM++) ./models/modelscope:/root/.cache/modelscope # HuggingFace models (Qwen3-ASR, GPU only) ./models/huggingface:/root/.cache/huggingface
First run downloads models automatically. Pre-download for offline deployment:
bash# Use the helper script (recommended) ./scripts/prepare-models.sh # Or manually with Docker docker run --rm \ -v ./models/modelscope:/root/.cache/modelscope \ -v ./models/huggingface:/root/.cache/huggingface \ quantatrisk/funasr-api:gpu-latest \ python -c "from app.utils.download_models import download_models; download_models()"
Resource Requirements
Minimum (CPU):
- CPU: 4 cores
- Memory: 16GB
- Disk: 20GB
Recommended (GPU):
- CPU: 4 cores
- Memory: 16GB
- GPU: NVIDIA GPU (16GB+ VRAM)
- Disk: 20GB
Links
- GitHub: https://github.com/Quantatirsk/funasr-api
- Documentation: https://github.com/Quantatirsk/funasr-api/tree/main/docs
- Issue Tracker: https://github.com/Quantatirsk/funasr-api/issues
License
MIT License
镜像拉取方式
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本，请访问 标签列表页面。
轩辕镜像加速拉取命令点我查看更多 funasr-api 镜像标签
docker pull docker.xuanyuan.run/quantatrisk/funasr-api:<标签>
DockerHub 原生拉取命令
docker pull quantatrisk/funasr-api:<标签>
镜像拉取常见问题
功能
错误码
用户好评
来自真实用户的反馈，见证轩辕镜像的优质服务
oldzhang
运维工程师
Linux服务器
5
"Docker访问体验非常流畅，大镜像也能快速完成下载。"