Kokoro-FastAPI---CPU
Docker 应用程序 from grtgbln's Repository
概述
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching.
This is a version meant for running on CPUs. It is not recommended to run this on a CPU unless you have a very powerful CPU, as it will be slow. If you have a GPU, please use the GPU version of this container.
This is a version meant for running on CPUs. It is not recommended to run this on a CPU unless you have a very powerful CPU, as it will be slow. If you have a GPU, please use the GPU version of this container.
运行时参数
- 网络用户界面
http://[IP]:[PORT:8880]/- 网络
bridge- 特权
- false
模板配置
Web UI PortPorttcp
Container Port: 8880
- 目标
- 8880
- 默认值
- 8880
- 价值
- 8880
Download ModelVariable
Download model on start
- 目标
- DOWNLOAD_MODEL
- 默认值
- true|false
App DataPath
Path to the app data folder
- 目标
- /app/api
- 默认值
- /mnt/user/appdata/kokoro-fastapi/data
- 价值
- /mnt/user/appdata/kokoro-fastapi/data
Python PathVariable
Python path environment variable
- 目标
- PYTHONPATH
- 默认值
- /app:/app/api
- 价值
- /app:/app/api
ONNX Optimization - Thread CountVariable
Number of threads to use for ONNX model inference
- 目标
- ONNX_NUM_THREADS
- 默认值
- 8
- 价值
- 8
ONNX Optimization - Inter Op Thread CountVariable
ONNX inter operation thread count
- 目标
- ONNX_INTER_OP_THREADS
- 默认值
- 4
- 价值
- 4
ONNX Optimization - Execution ModeVariable
ONNX execution mode
- 目标
- ONNX_EXECUTION_MODE
- 默认值
- parallel
- 价值
- parallel
ONNX Optimization - Optimization LevelVariable
ONNX optimization level
- 目标
- ONNX_OPTIMIZATION_LEVEL
- 默认值
- all
- 价值
- all
ONNX Optimization - Memory PatternVariable
Enable ONNX memory pattern optimization
- 目标
- ONNX_MEMORY_PATTERN
- 默认值
- true
- 价值
- true
ONNX Optimization - Arena Extend StrategyVariable
ONNX arena extend strategy
- 目标
- ONNX_ARENA_EXTEND_STRATEGY
- 默认值
- kNextPowerOfTwo
- 价值
- kNextPowerOfTwo
Log LevelVariable
Logging level for the API
- 目标
- API_LOG_LEVEL
- 默认值
- DEBUG
- 价值
- DEBUG
详细信息
存储库
ghcr.io/remsky/kokoro-fastapi-cpu:latest最后更新2026-05-31
初见2025-04-25
在Unraid 上运行 Kokoro-FastAPI---CPU 。
Kokoro-FastAPI---CPU 已被列入Unraid OS 的社区应用程序。探索Unraid ，构建灵活的家庭服务器、NAS 或家庭实验室。