Files

T

peanut 89fc42819d feat: AI 场景路由、ASR 服务及前后端全链路同步

- 新增 AI 场景路由控制器和管理接口
- 新增 ASR 语音识别服务及前后端集成
- 同步 AI Runtime 客户端到 Web/小程序/Life-Script
- 完善 AI 配置测试修复和管理后台路由配置
- 新增数据库迁移脚本

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-23 13:25:21 +08:00

app.py

feat: AI 场景路由、ASR 服务及前后端全链路同步

2026-05-23 13:25:21 +08:00

emotion-museum-asr.service

feat: AI 场景路由、ASR 服务及前后端全链路同步

2026-05-23 13:25:21 +08:00

README.md

feat: AI 场景路由、ASR 服务及前后端全链路同步

2026-05-23 13:25:21 +08:00

requirements.txt

feat: AI 场景路由、ASR 服务及前后端全链路同步

2026-05-23 13:25:21 +08:00

README.md

Emotion Museum ASR Service

Private speech-to-text service for the mini program voice input.

Install on 101.200.208.45:

cd /data/programs/emotion-museum/asr-service
python3.11 -m venv .venv
. .venv/bin/activate
pip install -r requirements.txt

uvicorn app:app --host 127.0.0.1 --port 19120
curl http://127.0.0.1:19120/health

The service uses FunASR ONNX Runtime with a local Chinese Paraformer model on CPU and is intended to stay private on localhost. The Java backend exposes the authenticated public API.