arwin0727's picture
Upload folder using huggingface_hub
3303abf verified
# docker/Dockerfile
# IMPORTANT: The docker images do not contain the checkpoints. You need to mount the checkpoints to the container.
# Build the image:
# docker build \
# --platform linux/amd64 \
# -f docker/Dockerfile \
# --build-arg BACKEND=[cuda, cpu] \
# --target [webui, server] \
# -t fish-speech-[webui, server]:[cuda, cpu] .
# e.g. for building the webui:
# docker build \
# --platform linux/amd64 \
# -f docker/Dockerfile \
# --build-arg BACKEND=cuda \
# --target webui \
# -t fish-speech-webui:cuda .
# e.g. for building the server:
# docker build \
# --platform linux/amd64 \
# -f docker/Dockerfile \
# --build-arg BACKEND=cuda \
# --target server \
# -t fish-speech-server:cuda .
# Multi-platform build:
# docker buildx build \
# --platform linux/amd64,linux/arm64 \
# -f docker/Dockerfile \
# --build-arg BACKEND=cpu \
# --target webui \
# -t fish-speech-webui:cpu .
# Running the image interactively:
# docker run \
# --gpus all \
# -v /path/to/fish-speech/checkpoints:/app/checkpoints \
# -e COMPILE=1 \ ... or -e COMPILE=0 \
# -it fish-speech-[webui, server]:[cuda, cpu]
# E.g. running the webui:
# docker run \
# --gpus all \
# -v ./checkpoints:/app/checkpoints \
# -e COMPILE=1 \
# -p 7860:7860 \
# fish-speech-webui:cuda
# E.g. running the server:
# docker run \
# --gpus all \
# -v ./checkpoints:/app/checkpoints \
# -p 8080:8080 \
# -it fish-speech-server:cuda
# Select the specific cuda version (see https://hub.docker.com/r/nvidia/cuda/)
ARG CUDA_VER=12.9.0
# Adapt the uv extra to fit the cuda version (one of [cu126, cu128, cu129])
ARG UV_EXTRA=cu129
ARG BACKEND=cuda
ARG UBUNTU_VER=24.04
ARG PY_VER=3.12
ARG UV_VERSION=0.8.15
# Create non-root user early for security
ARG USERNAME=fish
ARG USER_UID=1000
ARG USER_GID=1000
##############################################################
# Base stage per backend
##############################################################
# --- CUDA (x86_64) ---
FROM nvidia/cuda:${CUDA_VER}-cudnn-runtime-ubuntu${UBUNTU_VER} AS base-cuda
ENV DEBIAN_FRONTEND=noninteractive
# Install system dependencies in a single layer with cleanup
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
set -eux \
&& rm -f /etc/apt/apt.conf.d/docker-clean \
&& echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache \
&& apt-get update \
&& apt-get install -y --no-install-recommends \
python3-pip \
python3-dev \
git \
ca-certificates \
curl \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# --- CPU-only (portable x86_64) ---
FROM python:${PY_VER}-slim AS base-cpu
ENV UV_EXTRA=cpu
# Install system dependencies in a single layer with cleanup
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
set -eux \
&& rm -f /etc/apt/apt.conf.d/docker-clean \
&& echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache \
&& apt-get update \
&& apt-get install -y --no-install-recommends \
git \
ca-certificates \
curl \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
##############################################################
# UV stage
##############################################################
ARG UV_VERSION
FROM ghcr.io/astral-sh/uv:${UV_VERSION} AS uv-bin
##############################################################
# Shared app base stage
##############################################################
FROM base-${BACKEND} AS app-base
ARG PY_VER
ARG BACKEND
ARG USERNAME
ARG USER_UID
ARG USER_GID
ARG UV_VERSION
ARG UV_EXTRA
ENV BACKEND=${BACKEND} \
DEBIAN_FRONTEND=noninteractive \
PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1
# System dependencies for audio processing
ARG DEPENDENCIES=" \
libsox-dev \
build-essential \
cmake \
libasound-dev \
portaudio19-dev \
libportaudio2 \
libportaudiocpp0 \
ffmpeg"
# Install system dependencies with caching and cleanup
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
set -eux \
&& rm -f /etc/apt/apt.conf.d/docker-clean \
&& echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache \
&& apt-get update \
&& apt-get install -y --no-install-recommends ${DEPENDENCIES} \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# Install specific uv version
COPY --from=uv-bin /uv /uvx /bin/
# RUN groupadd --gid ${USER_GID} ${USERNAME} \
# && useradd --uid ${USER_UID} --gid ${USER_GID} -m ${USERNAME} \
# && mkdir -p /app /home/${USERNAME}/.cache \
# && chown -R ${USERNAME}:${USERNAME} /app /home/${USERNAME}/.cache
# Create non-root user (or use existing user)
RUN set -eux; \
if getent group ${USER_GID} >/dev/null 2>&1; then \
echo "Group ${USER_GID} already exists"; \
else \
groupadd -g ${USER_GID} ${USERNAME}; \
fi; \
if id -u ${USER_UID} >/dev/null 2>&1; then \
echo "User ${USER_UID} already exists, using existing user"; \
EXISTING_USER=$(id -un ${USER_UID}); \
mkdir -p /app /home/${EXISTING_USER}/.cache; \
chown -R ${USER_UID}:${USER_GID} /app /home/${EXISTING_USER}/.cache; \
else \
useradd -m -u ${USER_UID} -g ${USER_GID} ${USERNAME}; \
mkdir -p /app /home/${USERNAME}/.cache; \
chown -R ${USERNAME}:${USERNAME} /app /home/${USERNAME}/.cache; \
fi
# Create references directory with proper permissions for the non-root user
RUN mkdir -p /app/references \
&& chown -R ${USER_UID}:${USER_GID} /app/references \
&& chmod 755 /app/references
# Set working directory
WORKDIR /app
# Copy dependency files first for better caching
COPY --chown=${USER_UID}:${USER_GID} pyproject.toml uv.lock README.md ./
# Switch to non-root user for package installation
USER ${USER_UID}:${USER_GID}
# Install Python dependencies (cacheable by lockfiles)
# Use a generic cache path that works regardless of username
RUN --mount=type=cache,target=/tmp/uv-cache,uid=${USER_UID},gid=${USER_GID} \
uv python pin ${PY_VER} \
&& uv sync --extra ${UV_EXTRA} --frozen --no-install-project
# Copy application code
COPY --chown=${USER_UID}:${USER_GID} . .
# Install the local package after copying source code
RUN uv sync --extra ${UV_EXTRA} --frozen
# Create common entrypoint script
RUN printf '%s\n' \
'#!/bin/bash' \
'set -euo pipefail' \
'' \
'# Set user info from build args' \
'USER_UID='${USER_UID} \
'USER_GID='${USER_GID} \
'' \
'# Logging function' \
'log() { echo "[$(date +"%Y-%m-%d %H:%M:%S")] $*" >&2; }' \
'' \
'# Validate environment' \
'validate_env() {' \
' if [ ! -d "/app/checkpoints" ]; then' \
' log "WARNING: /app/checkpoints directory not found. Please mount your checkpoints."' \
' fi' \
' if [ ! -d "/app/references" ]; then' \
' log "WARNING: /app/references directory not found. Please mount your references."' \
' else' \
' # Check if we can write to references directory' \
' if [ ! -w "/app/references" ]; then' \
' log "ERROR: Cannot write to /app/references directory. Please ensure the mounted directory has proper permissions for user with UID ${USER_UID}."' \
' log "You can fix this by running: sudo chown -R ${USER_UID}:${USER_GID} /path/to/your/references"' \
' exit 1' \
' fi' \
' fi' \
'}' \
'' \
'# Build device arguments' \
'build_device_args() {' \
' if [ "${BACKEND:-}" = "cpu" ]; then' \
' echo "--device cpu"' \
' fi' \
'}' \
'' \
'# Build compile arguments' \
'build_compile_args() {' \
' if [ "${1:-}" = "compile" ] || [ "${COMPILE:-}" = "1" ] || [ "${COMPILE:-}" = "true" ]; then' \
' echo "--compile"' \
' shift' \
' fi' \
' echo "$@"' \
'}' \
'' \
'# Health check function' \
'health_check() {' \
' local port=${1:-7860}' \
' local endpoint=${2:-/health}' \
' curl -f http://localhost:${port}${endpoint} 2>/dev/null || exit 1' \
'}' \
> /app/common.sh && chmod +x /app/common.sh
##############################################################
# App stages
##############################################################
# Gradio WebUI
FROM app-base AS webui
ENV PYTHONDONTWRITEBYTECODE=1 PYTHONUNBUFFERED=1
ARG GRADIO_SERVER_NAME="0.0.0.0"
ARG GRADIO_SERVER_PORT=7860
ARG LLAMA_CHECKPOINT_PATH="checkpoints/s2-pro"
ARG DECODER_CHECKPOINT_PATH="checkpoints/s2-pro/codec.pth"
ARG DECODER_CONFIG_NAME="modded_dac_vq"
# Expose port
EXPOSE ${GRADIO_SERVER_PORT}
# Set environment variables
ENV GRADIO_SERVER_NAME=${GRADIO_SERVER_NAME}
ENV GRADIO_SERVER_PORT=${GRADIO_SERVER_PORT}
ENV LLAMA_CHECKPOINT_PATH=${LLAMA_CHECKPOINT_PATH}
ENV DECODER_CHECKPOINT_PATH=${DECODER_CHECKPOINT_PATH}
ENV DECODER_CONFIG_NAME=${DECODER_CONFIG_NAME}
# Create webui entrypoint
RUN printf '%s\n' \
'#!/bin/bash' \
'source /app/common.sh' \
'' \
'log "Starting Fish Speech WebUI..."' \
'validate_env' \
'' \
'DEVICE_ARGS=$(build_device_args)' \
'COMPILE_ARGS=$(build_compile_args "$@")' \
'' \
'log "Device args: ${DEVICE_ARGS:-none}"' \
'log "Compile args: ${COMPILE_ARGS}"' \
'log "Server: ${GRADIO_SERVER_NAME}:${GRADIO_SERVER_PORT}"' \
'' \
'exec uv run tools/run_webui.py \' \
' --llama-checkpoint-path "${LLAMA_CHECKPOINT_PATH}" \' \
' --decoder-checkpoint-path "${DECODER_CHECKPOINT_PATH}" \' \
' --decoder-config-name "${DECODER_CONFIG_NAME}" \' \
' ${DEVICE_ARGS} ${COMPILE_ARGS}' \
> /app/start_webui.sh && chmod +x /app/start_webui.sh
# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
CMD curl -f http://localhost:${GRADIO_SERVER_PORT}/health || exit 1
ENTRYPOINT ["/app/start_webui.sh"]
# API Server
FROM app-base AS server
ENV PYTHONDONTWRITEBYTECODE=1 PYTHONUNBUFFERED=1
ARG API_SERVER_NAME="0.0.0.0"
ARG API_SERVER_PORT=8080
ARG LLAMA_CHECKPOINT_PATH="checkpoints/s2-pro"
ARG DECODER_CHECKPOINT_PATH="checkpoints/s2-pro/codec.pth"
ARG DECODER_CONFIG_NAME="modded_dac_vq"
# Expose port
EXPOSE ${API_SERVER_PORT}
# Set environment variables
ENV API_SERVER_NAME=${API_SERVER_NAME}
ENV API_SERVER_PORT=${API_SERVER_PORT}
ENV LLAMA_CHECKPOINT_PATH=${LLAMA_CHECKPOINT_PATH}
ENV DECODER_CHECKPOINT_PATH=${DECODER_CHECKPOINT_PATH}
ENV DECODER_CONFIG_NAME=${DECODER_CONFIG_NAME}
# Create server entrypoint
RUN printf '%s\n' \
'#!/bin/bash' \
'source /app/common.sh' \
'' \
'log "Starting Fish Speech API Server..."' \
'validate_env' \
'' \
'DEVICE_ARGS=$(build_device_args)' \
'COMPILE_ARGS=$(build_compile_args "$@")' \
'' \
'log "Device args: ${DEVICE_ARGS:-none}"' \
'log "Compile args: ${COMPILE_ARGS}"' \
'log "Server: ${API_SERVER_NAME}:${API_SERVER_PORT}"' \
'' \
'exec uv run tools/api_server.py \' \
' --listen "${API_SERVER_NAME}:${API_SERVER_PORT}" \' \
' --llama-checkpoint-path "${LLAMA_CHECKPOINT_PATH}" \' \
' --decoder-checkpoint-path "${DECODER_CHECKPOINT_PATH}" \' \
' --decoder-config-name "${DECODER_CONFIG_NAME}" \' \
' ${DEVICE_ARGS} ${COMPILE_ARGS}' \
> /app/start_server.sh && chmod +x /app/start_server.sh
# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
CMD curl -f http://localhost:${API_SERVER_PORT}/v1/health || exit 1
ENTRYPOINT ["/app/start_server.sh"]
# Development stage
FROM app-base AS dev
USER root
# Install development tools
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
apt-get update \
&& apt-get install -y --no-install-recommends \
vim \
htop \
strace \
gdb \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
USER ${USER_UID}:${USER_GID}
# Install development dependencies
RUN uv sync --extra ${UV_EXTRA} --dev
# Default to bash for development
ENTRYPOINT ["/bin/bash"]