Introduce Docker and Windows CI Workflow, Pre-commit Formatting, and Language Resource Auto-Download (#2351)

* Docker Auto-Build Workflow * Rename * Update * Fix Bugs * Disable Progress Bar When workflows triggered * Fix Wget * Fix Bugs * Fix Bugs * Update Wget * Update Workflows * Accelerate Docker Image Building * Fix Install.sh * Add Skip-Check For Action Runner * Fix Dockerfile * . * . * . * . * Delete File in Runner * Add Sort * Delete More Files * Delete More * . * . * . * Add Pre-Commit Hook Update Docker * Add Code Spell Check * [pre-commit.ci] trigger * [pre-commit.ci] trigger * [pre-commit.ci] trigger * Fix Bugs * . * Disable Progress Bar and Logs while using GitHub Actions * . * . * Fix Bugs * update conda * fix bugs * Fix Bugs * fix bugs * . * . * Quiet Installation * fix bugs * . * fix bug * . * Fix pre-commit.ci and Docker * fix bugs * . * Update Docker & Pre-Commit * fix bugs * Update Req * Update Req * Update OpenCC * update precommit * . * Update .pre-commit-config.yaml * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update Docs and fix bugs * Fix \ * Fix MacOS * . * test * . * Add Tag Alias * . * fix bugs * fix bugs * make image smaller * update pre-commit config * . * . * fix bugs * use miniconda * Fix Wrong Path * . * debug * debug * revert * Fix Bugs * Update Docs, Add Dict Auto Download in install.sh * update docker_build * Update Docs for Install.sh * update docker docs about architecture * Add Xcode-Commandline-Tool Installation * Update Docs 1. Add Missing VC17 2. Modufied the Order of FFmpeg Installation and Requirements Installation 3. Remove Duplicate FFmpeg * Fix Wrong Cuda Version * Update TESTED ENV * Add PYTHONNOUSERSITE(-s) * Fix Wrapper * Update install.sh For Robustness * Ignore .git * Preload CUDNN For Ctranslate2 * Remove Gradio Warnings * Update Colab * Fix OpenCC Problems * Update Win DLL Strategy * Fix Onnxruntime-gpu NVRTC Error * Fix Path Problems * Add Windows Packages Workflow * WIP * WIP * WIP * WIP * WIP * WIP * . * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * WIP * Fix Path * Fix Path * Enable Logging * Set 7-Zip compression level to maximum (-mx=9) * Use Multithread in ONNX Session * Fix Tag Bugs * Add Time * Add Time * Add Time * Compress More * Copy DLL to Solve VC Runtime DLL Missing Issues * Expose FFmpeg Errors, Copy Only Part of Visual C++ Runtime * Update build_windows_packages.ps1 * Update build_windows_packages.ps1 * Update build_windows_packages.ps1 * Update build_windows_packages.ps1 * WIP * WIP * WIP * Update build_windows_packages.ps1 * Update install.sh * Update build_windows_packages.ps1 * Update docker-publish.yaml * Update install.sh * Update Dockerfile * Update docker_build.sh * Update miniconda_install.sh * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update Colab-WebUI.ipynb * Update Colab-Inference.ipynb * Update docker-compose.yaml * 更新 build_windows_packages.ps1 * Update install.sh --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-05-26 05:45:14 +03:00
parent 13055fa569
commit d5e479dad6
58 changed files with 2096 additions and 987 deletions
--- a/Docker/damo.sha256
+++ b/Docker/damo.sha256
@@ -1,3 +0,0 @@
-5bba782a5e9196166233b9ab12ba04cadff9ef9212b4ff6153ed9290ff679025 /workspace/tools/damo_asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.pb
-b3be75be477f0780277f3bae0fe489f48718f585f3a6e45d7dd1fbb1a4255fc5 /workspace/tools/damo_asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch/model.pb
-a5818bb9d933805a916eebe41eb41648f7f9caad30b4bd59d56f3ca135421916 /workspace/tools/damo_asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/model.pb
--- a/Docker/download.py
+++ b/Docker/download.py
@@ -1,8 +0,0 @@
-# Download moda ASR related models
-from modelscope import snapshot_download
-
-model_dir = snapshot_download(
-    "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", revision="v2.0.4"
-)
-model_dir = snapshot_download("damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", revision="v2.0.4")
-model_dir = snapshot_download("damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch", revision="v2.0.4")
--- a/Docker/download.sh
+++ b/Docker/download.sh
@@ -1,11 +0,0 @@
-#!/usr/bin/env bash
-
-set -Eeuo pipefail
-
-echo "Downloading models..."
-
-aria2c --disable-ipv6 --input-file /workspace/Docker/links.txt --dir /workspace --continue
-
-echo "Checking SHA256..."
-
-parallel --will-cite -a /workspace/Docker/links.sha256 "echo -n {} | sha256sum -c"
--- a/Docker/install_wrapper.sh
+++ b/Docker/install_wrapper.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" &>/dev/null && pwd)"
+
+cd "$SCRIPT_DIR" || exit 1
+
+cd .. || exit 1
+
+set -e
+
+source "$HOME/miniconda3/etc/profile.d/conda.sh"
+
+mkdir -p GPT_SoVITS
+
+mkdir -p GPT_SoVITS/text
+
+ln -s /workspace/models/pretrained_models /workspace/GPT-SoVITS/GPT_SoVITS/pretrained_models
+
+ln -s /workspace/models/G2PWModel /workspace/GPT-SoVITS/GPT_SoVITS/text/G2PWModel
+
+bash install.sh --device "CU${CUDA_VERSION//./}" --source HF
+
+pip cache purge
+
+pip show torch
+
+rm -rf /tmp/* /var/tmp/*
+
+rm -rf "$HOME/miniconda3/pkgs"
+
+mkdir -p "$HOME/miniconda3/pkgs"
+
+rm -rf /root/.conda /root/.cache
--- a/Docker/links.sha256
+++ b/Docker/links.sha256
@@ -1,12 +0,0 @@
-b1c1e17e9c99547a89388f72048cd6e1b41b5a18b170e86a46dfde0324d63eb1 /workspace/GPT_SoVITS/pretrained_models/s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt
-fc579c1db3c1e21b721001cf99d7a584214280df19b002e200b630a34fa06eb8 /workspace/GPT_SoVITS/pretrained_models/s2D488k.pth
-020a014e1e01e550e510f2f61fae5e5f5b6aab40f15c22f1f12f724df507e835 /workspace/GPT_SoVITS/pretrained_models/s2G488k.pth
-24164f129c66499d1346e2aa55f183250c223161ec2770c0da3d3b08cf432d3c /workspace/GPT_SoVITS/pretrained_models/chinese-hubert-base/pytorch_model.bin
-e53a693acc59ace251d143d068096ae0d7b79e4b1b503fa84c9dcf576448c1d8 /workspace/GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/pytorch_model.bin
-39796caa5db18d7f9382d8ac997ac967bfd85f7761014bb807d2543cc844ef05 /workspace/tools/uvr5/uvr5_weights/HP2_all_vocals.pth
-45e6b65199e781b4a6542002699be9f19cd3d1cb7d1558bc2bfbcd84674dfe28 /workspace/tools/uvr5/uvr5_weights/HP3_all_vocals.pth
-5908891829634926119720241e8573d97cbeb8277110a7512bdb0bd7563258ee /workspace/tools/uvr5/uvr5_weights/HP5_only_main_vocal.pth
-8c8fd1582f9aabc363e47af62ddb88df6cae7e064cae75bbf041a067a5e0aee2 /workspace/tools/uvr5/uvr5_weights/VR-DeEchoAggressive.pth
-01376dd2a571bf3cb9cced680732726d2d732609d09216a610b0d110f133febe /workspace/tools/uvr5/uvr5_weights/VR-DeEchoDeReverb.pth
-56aba59db3bcdd14a14464e62f3129698ecdea62eee0f003b9360923eb3ac79e /workspace/tools/uvr5/uvr5_weights/VR-DeEchoNormal.pth
-233bb5c6aaa365e568659a0a81211746fa881f8f47f82d9e864fce1f7692db80 /workspace/tools/uvr5/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx
--- a/Docker/links.txt
+++ b/Docker/links.txt
@@ -1,34 +0,0 @@
-# GPT-SoVITS models
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/s1bert25hz-2kh-longer-epoch%3D68e-step%3D50232.ckpt
-  out=GPT_SoVITS/pretrained_models/s1bert25hz-2kh-longer-epoch=68e-step=50232.ckpt
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/s2D488k.pth
-  out=GPT_SoVITS/pretrained_models/s2D488k.pth
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/s2G488k.pth
-  out=GPT_SoVITS/pretrained_models/s2G488k.pth
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-hubert-base/config.json
-  out=GPT_SoVITS/pretrained_models/chinese-hubert-base/config.json
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-hubert-base/preprocessor_config.json
-  out=GPT_SoVITS/pretrained_models/chinese-hubert-base/preprocessor_config.json
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-hubert-base/pytorch_model.bin
-  out=GPT_SoVITS/pretrained_models/chinese-hubert-base/pytorch_model.bin
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-roberta-wwm-ext-large/config.json
-  out=GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/config.json
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-roberta-wwm-ext-large/pytorch_model.bin
-  out=GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/pytorch_model.bin
-https://huggingface.co/lj1995/GPT-SoVITS/resolve/main/chinese-roberta-wwm-ext-large/tokenizer.json
-  out=GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large/tokenizer.json
-# UVR5
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2_all_vocals.pth
-  out=tools/uvr5/uvr5_weights/HP2_all_vocals.pth
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP3_all_vocals.pth
-  out=tools/uvr5/uvr5_weights/HP3_all_vocals.pth
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5_only_main_vocal.pth
-  out=tools/uvr5/uvr5_weights/HP5_only_main_vocal.pth
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoAggressive.pth
-  out=tools/uvr5/uvr5_weights/VR-DeEchoAggressive.pth
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoDeReverb.pth
-  out=tools/uvr5/uvr5_weights/VR-DeEchoDeReverb.pth
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoNormal.pth
-  out=tools/uvr5/uvr5_weights/VR-DeEchoNormal.pth
-https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx
-  out=tools/uvr5/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx
--- a/Docker/miniconda_install.sh
+++ b/Docker/miniconda_install.sh
@@ -0,0 +1,70 @@
+#!/bin/bash
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" &>/dev/null && pwd)"
+
+cd "$SCRIPT_DIR" || exit 1
+
+cd .. || exit 1
+
+if [ -d "$HOME/miniconda3" ]; then
+    exit 0
+fi
+
+WORKFLOW=${WORKFLOW:-"false"}
+TARGETPLATFORM=${TARGETPLATFORM:-"linux/amd64"}
+
+if [ "$WORKFLOW" = "true" ]; then
+    WGET_CMD=(wget -nv --tries=25 --wait=5 --read-timeout=40 --retry-on-http-error=404)
+else
+    WGET_CMD=(wget --tries=25 --wait=5 --read-timeout=40 --retry-on-http-error=404)
+fi
+
+if [ "$TARGETPLATFORM" = "linux/amd64" ]; then
+    "${WGET_CMD[@]}" -O miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py311_25.3.1-1-Linux-x86_64.sh
+elif [ "$TARGETPLATFORM" = "linux/arm64" ]; then
+    "${WGET_CMD[@]}" -O miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py311_25.3.1-1-Linux-aarch64.sh
+else
+    exit 1
+fi
+
+LOG_PATH="/tmp/miniconda-install.log"
+
+bash miniconda.sh -b -p "$HOME/miniconda3" >"$LOG_PATH" 2>&1
+
+if [ $? -eq 0 ]; then
+    echo "== Miniconda Installed =="
+else
+    echo "Failed to Install miniconda"
+    tail -n 50 "$LOG_PATH"
+    exit 1
+fi
+
+rm miniconda.sh
+
+source "$HOME/miniconda3/etc/profile.d/conda.sh"
+
+"$HOME/miniconda3/bin/conda" config --add channels conda-forge
+
+"$HOME/miniconda3/bin/conda" update -q --all -y 1>/dev/null
+
+"$HOME/miniconda3/bin/conda" install python=3.11 -q -y
+
+"$HOME/miniconda3/bin/conda" install gcc=14 gxx ffmpeg cmake make unzip -q -y
+
+if [ "$CUDA_VERSION" = "12.8" ]; then
+    "$HOME/miniconda3/bin/pip" install torch torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/cu128
+elif [ "$CUDA_VERSION" = "12.6" ]; then
+    "$HOME/miniconda3/bin/pip" install torch==2.6 torchaudio --no-cache-dir --index-url https://download.pytorch.org/whl/cu126
+fi
+
+"$HOME/miniconda3/bin/pip" cache purge
+
+rm $LOG_PATH
+
+rm -rf "$HOME/miniconda3/pkgs"
+
+mkdir -p "$HOME/miniconda3/pkgs"
+
+rm -rf "$HOME/.conda" "$HOME/.cache"