Kokoro-FastAPI---CPU
Kokoro-FastAPI---CPU
Aplicación Docker from grtgbln's Repository
Visión general
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.
Argumentos en tiempo de ejecución
- Interfaz web
http://[IP]:[PORT:8880]/- Red
bridge- Privilegiado
- false
Configuración de plantillas
Web UI PortPorttcp
Container Port: 8880
- Objetivo
- 8880
- Por defecto
- 8880
- Valor
- 8880
Download ModelVariable
Download model on start
- Objetivo
- DOWNLOAD_MODEL
- Por defecto
- true|false
App DataPath
Path to the app data folder
- Objetivo
- /app/api
- Por defecto
- /mnt/user/appdata/kokoro-fastapi/data
- Valor
- /mnt/user/appdata/kokoro-fastapi/data
Python PathVariable
Python path environment variable
- Objetivo
- PYTHONPATH
- Por defecto
- /app:/app/api
- Valor
- /app:/app/api
ONNX Optimization - Thread CountVariable
Number of threads to use for ONNX model inference
- Objetivo
- ONNX_NUM_THREADS
- Por defecto
- 8
- Valor
- 8
ONNX Optimization - Inter Op Thread CountVariable
ONNX inter operation thread count
- Objetivo
- ONNX_INTER_OP_THREADS
- Por defecto
- 4
- Valor
- 4
ONNX Optimization - Execution ModeVariable
ONNX execution mode
- Objetivo
- ONNX_EXECUTION_MODE
- Por defecto
- parallel
- Valor
- parallel
ONNX Optimization - Optimization LevelVariable
ONNX optimization level
- Objetivo
- ONNX_OPTIMIZATION_LEVEL
- Por defecto
- all
- Valor
- all
ONNX Optimization - Memory PatternVariable
Enable ONNX memory pattern optimization
- Objetivo
- ONNX_MEMORY_PATTERN
- Por defecto
- true
- Valor
- true
ONNX Optimization - Arena Extend StrategyVariable
ONNX arena extend strategy
- Objetivo
- ONNX_ARENA_EXTEND_STRATEGY
- Por defecto
- kNextPowerOfTwo
- Valor
- kNextPowerOfTwo
Log LevelVariable
Logging level for the API
- Objetivo
- API_LOG_LEVEL
- Por defecto
- DEBUG
- Valor
- DEBUG
Categorías
Detalles
Repositorio
ghcr.io/remsky/kokoro-fastapi-cpu:latestÚltima actualización2026-05-31
Visto por primera vez2025-04-25
Ejecute Kokoro-FastAPI---CPU en Unraid.
Kokoro-FastAPI---CPU se encuentra en Community Apps para Unraid OS. Explore Unraid para crear un servidor doméstico flexible, un NAS o un laboratorio doméstico.