V 3.1.7

1. 移除软件包自带的本地 whisper（需单独安装）
2. 重构版本底层依赖，移除外部依赖
3. 修复 首页 暗黑模式不兼容的问题
4. 修复 SD 合并提示词报错

.gitignore

@@ -30,3 +30,13 @@ resources/config*
 *.log*
 resources/scripts/db/book.realm.lock
 resources/scripts/db/software.realm.lock
+resources/scripts/localWhisper/__pycache__/*
+resources/scripts/laitool/.venv
+resources/scripts/laitool/build
+resources/scripts/laitool/dist
+resources/scripts/localWhisper/build/*
+resources/scripts/__pycache__/*
+resources/scripts/db/*
+resources/scripts/localWhisper/.venv/*
+resources/scripts/localWhisper/_internal/*
+resources/scripts/localWhisper/local_whisper.exe

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "laitool",
-  "version": "3.1.6",
+  "version": "3.1.7",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "laitool",
-      "version": "3.1.6",
+      "version": "3.1.7",
       "hasInstallScript": true,
       "dependencies": {
         "@alicloud/alimt20181012": "^1.2.0",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "laitool",
-  "version": "3.1.6",
+  "version": "3.1.7",
   "description": "An AI tool for image processing, video processing, and other functions.",
   "main": "./out/main/index.js",
   "author": "laitool.cn",
@@ -84,6 +84,7 @@
       "resources/image/style/**",
       "resources/image/zhanwei.png",
       "resources/scripts/model/**",
+      "resources/scripts/Lai.exe",
       "resources/scripts/discordScript.js",
       "resources/tmp/**",
       "resources/icon.ico"

resources/scripts/Lai.py

@@ -4,7 +4,6 @@ import json
 import os
 import sys
 import clip
-import getgrame
 import Push_back_Prompt
 import public_tools
 import shotSplit
@@ -56,6 +55,8 @@ if sys.argv[1] == "-c":
     clip = clip.Clip(cript_directory, sys.argv[2], sys.argv[3])
     clip.MergeVideosAndClip()
     pass
+
+
 # 获取字体
 elif sys.argv[1] == "-f":
     # 获取本地已安装的字幕。然后返回
@@ -77,22 +78,17 @@ elif sys.argv[1] == "-p":
     Push_back_Prompt.init(sys.argv[2], sys.argv[3], sys.argv[4])
     pass
 
-# 剪映抽帧
-elif sys.argv[1] == "-k":
-    # print("")
-    getgrame.init(sys.argv[2], sys.argv[3], sys.argv[4])
-    pass
-
 elif sys.argv[1] == "-ka":
     shotSplit.get_fram(sys.argv[2], sys.argv[3], sys.argv[4])
     pass
 
-# 智能分镜。字幕识别
+# # 智能分镜。字幕识别
-elif sys.argv[1] == "-a":
+# elif sys.argv[1] == "-a":
-    print("开始算法分镜：" + sys.argv[2] + " -- 输出文件夹：" + sys.argv[3])
+#     print("开始算法分镜：" + sys.argv[2] + " -- 输出文件夹：" + sys.argv[3])
-    shotSplit.init(sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5], sys.argv[6])
+#     shotSplit.init(sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5], sys.argv[6])
-# 本地提取音频
+
-elif sys.argv[1] == "-t":
+# # 本地提取音频
-    print("开始提取文字：" + sys.argv[2])
+# elif sys.argv[1] == "-t":
-    shotSplit.GetTextTask(sys.argv[2], sys.argv[3], sys.argv[4])
+#     print("开始提取文字：" + sys.argv[2])
-    pass
+#     shotSplit.GetTextTask(sys.argv[2], sys.argv[3], sys.argv[4])
+#     pass

resources/scripts/Lai.spec

@@ -1,36 +1,34 @@
 # -*- mode: python ; coding: utf-8 -*-
 
-from PyInstaller.building.datastruct import Tree
-from PyInstaller.utils.hooks import get_package_paths
-
-PACKAGE_DIRECTORY = get_package_paths('faster_whisper')[1]
-datas = [(PACKAGE_DIRECTORY, 'faster_whisper')]
-
 
 a = Analysis(
     ['Lai.py'],
     pathex=[],
     binaries=[],
-    datas=datas,
+    datas=[],
     hiddenimports=[],
     hookspath=[],
     hooksconfig={},
     runtime_hooks=[],
     excludes=[],
     noarchive=False,
+    optimize=0,
 )
 pyz = PYZ(a.pure)
 
 exe = EXE(
     pyz,
     a.scripts,
+    a.binaries,
+    a.datas,
     [],
-    exclude_binaries=True,
     name='Lai',
     debug=False,
     bootloader_ignore_signals=False,
     strip=False,
     upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
     console=True,
     disable_windowed_traceback=False,
     argv_emulation=False,
@@ -38,12 +36,3 @@ exe = EXE(
     codesign_identity=None,
     entitlements_file=None,
 )
-coll = COLLECT(
-    exe,
-    a.binaries,
-    a.datas,
-    strip=False,
-    upx=True,
-    upx_exclude=[],
-    name='Lai',
-)

resources/scripts/Lai_2.spec

@@ -1,11 +1,17 @@
 # -*- mode: python ; coding: utf-8 -*-
 
+from PyInstaller.building.datastruct import Tree
+from PyInstaller.utils.hooks import get_package_paths
+
+PACKAGE_DIRECTORY = get_package_paths('faster_whisper')[1]
+datas = [(PACKAGE_DIRECTORY, 'faster_whisper')]
+
 
 a = Analysis(
-    ['lama_inpaint.py'],
+    ['Lai.py'],
     pathex=[],
     binaries=[],
-    datas=[],
+    datas=datas,
     hiddenimports=[],
     hookspath=[],
     hooksconfig={},
@@ -18,16 +24,13 @@ pyz = PYZ(a.pure)
 exe = EXE(
     pyz,
     a.scripts,
-    a.binaries,
-    a.datas,
     [],
-    name='lama_inpaint',
+    exclude_binaries=True,
+    name='Lai',
     debug=False,
     bootloader_ignore_signals=False,
     strip=False,
     upx=True,
-    upx_exclude=[],
-    runtime_tmpdir=None,
     console=True,
     disable_windowed_traceback=False,
     argv_emulation=False,
@@ -35,3 +38,12 @@ exe = EXE(
     codesign_identity=None,
     entitlements_file=None,
 )
+coll = COLLECT(
+    exe,
+    a.binaries,
+    a.datas,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    name='Lai',
+)

resources/scripts/localWhisper/install.bat

@@ -0,0 +1,2 @@
+@echo off
+pyinstaller --upx-dir="C:\\Users\\27698\\Desktop\\upx-4.2.4-win64\upx.exe" local_whisper.py

resources/scripts/localWhisper/local_whisper.py

@@ -0,0 +1,170 @@
+# -*- coding: utf-8 -*-
+import io
+import os
+import sys
+import public_tools
+from pathlib import Path
+from huggingface_hub import hf_hub_download
+from faster_whisper import WhisperModel
+
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8")
+
+# 判断sys.argv 的长度，如果小于2，说明没有传入参数，设置初始参数
+# "C:\\Users\\27698\\Desktop\\LAITool\\resources\\scripts\\Lai.exe" -c "D:/来推项目集/7.4/娱乐：江湖大哥退休，去拍电影/scripts/output_crop_00001.json" "NVIDIA"
+# if len(sys.argv) < 2:
+#     sys.argv = [
+#         "C:\\Users\\27698\\Desktop\\LAITool\\resources\\scripts\\Lai.exe",
+#         "-w",
+#         "C:\\Users\\27698\\Desktop\\测试\\test\\mjTestoutput_crop_00001.mp4",
+#         "C:\\Users\\27698\\Desktop\\测试\\test\data\\frame",
+#         "C:\\Users\\27698\\Desktop\\测试\\test\\tmp\\input_crop",
+#         30,
+#         "NVIDIA",
+#     ]
+
+print(sys.argv)
+
+if len(sys.argv) < 2:
+    print("Params: <runtime-config.json>")
+    exit(0)
+
+if getattr(sys, "frozen", False):
+    cript_directory = os.path.dirname(sys.executable)
+elif __file__:
+    cript_directory = os.path.dirname(__file__)
+
+
+def GetText(out_folder, mp3_folder):
+    text = []
+    # 先获取模型
+    print("正在下载或加载模型")
+    sys.stdout.flush()
+    model_path = Path(
+        hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="preprocessor_config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="tokenizer.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="vocabulary.json",
+    )
+    model = WhisperModel(
+        model_size_or_path=os.path.dirname(model_path),
+        device="auto",
+        local_files_only=True,
+    )
+    print("模型加载成功，开始识别")
+    sys.stdout.flush()
+    # 拿到指定文件夹里面的所有的MP3文件
+    mp3_list = []
+    for root, dirs, files in os.walk(mp3_folder):
+        for file in files:
+            if file.endswith(".mp3"):
+                mp3_list.append(os.path.join(root, file))
+
+    for mp in mp3_list:
+        segments, info = model.transcribe(
+            mp,
+            beam_size=5,
+            language="zh",
+            vad_filter=True,
+            vad_parameters=dict(min_silence_duration_ms=1000),
+        )
+        tmp_text = ""
+        for segment in segments:
+            tmp_text += segment.text + "。"
+        print(mp + "识别完成")
+        sys.stdout.flush()
+        text.append(tmp_text)
+
+    # 数据写出
+    print("文本全部识别成功，正在写出")
+    sys.stdout.flush()
+    tools = public_tools.PublicTools()
+    tools.write_to_file(text, os.path.join(out_folder, "文案.txt"))
+    print("写出完成")
+    sys.stdout.flush()
+
+
+def GetTextTask(out_folder, mp, name):
+    text = []
+    # 先获取模型
+    print("正在下载或加载模型")
+    sys.stdout.flush()
+    model_path = Path(
+        hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="preprocessor_config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="tokenizer.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="vocabulary.json",
+    )
+    model = WhisperModel(
+        model_size_or_path=os.path.dirname(model_path),
+        device="auto",
+        local_files_only=True,
+    )
+    print("模型加载成功，开始识别")
+    sys.stdout.flush()
+    segments, info = model.transcribe(
+        mp,
+        beam_size=5,
+        language="zh",
+        vad_filter=True,
+        vad_parameters=dict(min_silence_duration_ms=1000),
+    )
+    tmp_text = ""
+    for segment in segments:
+        tmp_text += segment.text + "。"
+    print(mp + "识别完成")
+    sys.stdout.flush()
+    text.append(tmp_text)
+
+    # 数据写出
+    sys.stdout.flush()
+    tools = public_tools.PublicTools()
+    tools.write_to_file(text, os.path.join(out_folder, name + ".txt"))
+    sys.stdout.flush()
+
+
+# GetTextTask(
+#     "C:\\Users\\27698\\Desktop\\测试\\mjTest",
+#     "C:\\Users\\27698\\Desktop\\测试\\mjTest\\data\\frame\\00001.mp4",
+#     "00001",
+# )
+
+if sys.argv[1] == "-ts":
+    GetText(
+        sys.argv[2],
+        sys.argv[3],
+    )
+elif sys.argv[1] == "-t":
+    GetTextTask(
+        sys.argv[2],
+        sys.argv[3],
+        sys.argv[4],
+    )
+else:
+    print("Params: <runtime-config.json>")
+    exit(0)

resources/scripts/localWhisper/local_whisper.spec

@@ -0,0 +1,50 @@
+# -*- mode: python ; coding: utf-8 -*-
+
+from PyInstaller.building.datastruct import Tree
+from PyInstaller.utils.hooks import get_package_paths
+
+PACKAGE_DIRECTORY = get_package_paths('faster_whisper')[1]
+datas = [(PACKAGE_DIRECTORY, 'faster_whisper')]
+
+
+a = Analysis(
+    ['local_whisper.py'],
+    pathex=[],
+    binaries=[],
+    datas=[],
+    hiddenimports=[],
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+    optimize=0,
+)
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    [],
+    exclude_binaries=True,
+    name='local_whisper',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+)
+coll = COLLECT(
+    exe,
+    a.binaries,
+    a.datas,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    name='local_whisper',
+)

resources/scripts/localWhisper/public_tools.py

@@ -0,0 +1,351 @@
+# 读取文件的方法
+import json
+import os
+import win32api
+import win32con
+import pywintypes
+import shutil
+import re
+
+
+class PublicTools:
+    """
+    一些公用的基础方法
+    """
+
+    def delete_path(self, path):
+        """
+        删除指定路径的文件或者是文件夹
+        """
+        # 检查路径是否存在
+        if not os.path.exists(path):
+            return
+
+        # 检查路径是文件还是文件夹
+        if os.path.isfile(path):
+            # 是文件，执行删除
+            try:
+                os.remove(path)
+            except Exception as e:
+                raise e
+        elif os.path.isdir(path):
+            # 是文件夹，执行删除
+            try:
+                shutil.rmtree(path)
+            except Exception as e:
+                raise e
+        else:
+            raise
+
+    def list_files_by_extension(self, folder_path, extension):
+        """
+        读取指定文件夹下面的所有的指定拓展文件命的文件列表
+        """
+        file_list = []
+        for root, dirs, files in os.walk(folder_path):
+            for file in files:
+                if file.endswith(extension):
+                    file_list.append(os.path.join(root, file))
+                elif file.endswith(extension.upper()):
+                    file_list.append(os.path.join(root, file))
+        return file_list
+
+    def get_fonts_from_registry(self, key_path):
+        """
+        获取注册表中安装的字体文件
+        """
+        font_names = []
+        try:
+            key = win32api.RegOpenKeyEx(
+                (
+                    win32con.HKEY_LOCAL_MACHINE
+                    if "HKEY_LOCAL_MACHINE" in key_path
+                    else win32con.HKEY_CURRENT_USER
+                ),
+                key_path.split("\\", 1)[1],
+                0,
+                win32con.KEY_READ,
+            )
+            i = 0
+            while True:
+                try:
+                    value = win32api.RegEnumValue(key, i)
+                    font_name = value[0]
+                    # 使用正则表达式移除括号及其内容
+                    font_name = re.sub(r"\s*\([^)]*\)$", "", font_name)
+                    font_names.append(font_name)
+                    i += 1
+                except pywintypes.error as e:
+                    if e.winerror == 259:  # 没有更多的数据
+                        break
+                    else:
+                        raise
+        finally:
+            try:
+                win32api.RegCloseKey(key)
+            except:
+                pass
+        return font_names
+
+    def get_installed_fonts(self):
+        """
+        获取字体文件名称并返回
+        """
+        system_fonts = self.get_fonts_from_registry(
+            "HKEY_LOCAL_MACHINE\\SOFTWARE\\Microsoft\\Windows NT\\CurrentVersion\\Fonts"
+        )
+        user_fonts = self.get_fonts_from_registry(
+            "HKEY_CURRENT_USER\\Software\\Microsoft\\Windows NT\\CurrentVersion\\Fonts"
+        )
+        all_fonts = list(set(system_fonts + user_fonts))  # 合并并去重
+        return all_fonts
+
+    # 将RRGGBB转换为BBGGRR
+    def convert_rrggbb_to_bbggrr(self, rrggbb):
+        """
+        将RRGGBB转换为BBGGRR
+        """
+        if len(rrggbb) == 7:
+            rr = rrggbb[1:3]
+            gg = rrggbb[3:5]
+            bb = rrggbb[5:7]
+            return bb + gg + rr
+        else:
+            return "Invalid input"
+
+    def write_to_file(self, arr, filename):
+        with open(filename, "w",encoding='utf-8') as f:
+            for item in arr:
+                f.write("%s\n" % item)
+
+
+# 读取文件
+def read_file(fileType):
+    txt_path = input(f"输入{fileType}文件路径：")
+    txt_path = remove_prefix_and_suffix(txt_path, '"', '"')
+    while txt_path.strip() == "":
+        txt_path = input(f"输入{fileType}文件路径：")
+
+    while os.path.exists(txt_path) == False:
+        print("文件路径不存在错误：")
+        txt_path = input(f"输入{fileType}文件路径：")
+        txt_path = remove_prefix_and_suffix(txt_path, '"', '"')
+    return txt_path
+
+
+def format_time_ms(milliseconds):
+    """
+    时间转换将ms->小时:分钟:秒.毫秒格式
+    """
+    seconds = milliseconds / 1000
+    # 计算小时、分钟和秒
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    seconds = seconds % 60
+    # 格式化字符串
+    # 使用`%02d`确保小时和分钟总是显示为两位数，`%.2f`确保秒数显示两位小数
+    formatted_time = f"{hours}:{minutes:02d}:{seconds:05.2f}"
+    return formatted_time
+
+
+# 删除满足条件的开头和结尾
+def remove_prefix_and_suffix(input_str, prefix_to_remove, suffix_to_remove):
+    if input_str.startswith(prefix_to_remove):
+        # 删除开头
+        input_str = input_str[len(prefix_to_remove) :]
+
+    if input_str.endswith(suffix_to_remove):
+        # 删除结尾
+        input_str = input_str[: -len(suffix_to_remove)]
+
+    return input_str
+
+
+# 判断文件夹下面是不是有特定的文件夹
+def check_if_folder_exists(parent_folder, target_folder_name):
+    # 获取文件夹列表
+    subfolders = [f.name for f in os.scandir(parent_folder) if f.is_dir()]
+
+    # 检查特定文件夹是否存在
+    if target_folder_name in subfolders:
+        return True
+    else:
+        return False
+
+
+# 检查指定文件夹中是否存在特定文件。
+def file_exists_in_folder(folder_path: str, file_name: str) -> bool:
+    # 构建完整的文件路径
+    file_path = os.path.join(folder_path, file_name)
+
+    # 返回文件是否存在
+    return os.path.isfile(file_path)
+
+
+# 秒数转换，保留一位小数
+def convert_to_seconds(number, count):
+    seconds = number / 1000000
+    rounded_number = round(seconds, count)
+    return rounded_number
+
+
+def is_empty(obj):
+    if obj is None:
+        return True
+    elif isinstance(obj, str):
+        return len(obj) == 0
+    elif isinstance(obj, list):
+        return len(obj) == 0
+    elif isinstance(obj, dict):
+        return len(obj) == 0
+    return False
+
+
+def opt_dict(obj, key, default=None):
+    if obj is None:
+        return default
+    if key in obj:
+        v = obj[key]
+        if not is_empty(v):
+            return v
+    return default
+
+
+def read_config(path, webui=True):
+    with open(path, "r", encoding="utf-8") as f:
+        runtime_config = json.load(f)
+
+    if "config" not in runtime_config:
+        print("no filed 'config' in json")
+        return None
+
+    config = runtime_config["config"]
+    if "webui" not in config:
+        print("no filed 'webui' in 'config'")
+        return None
+
+    setting_config_path = config["setting"]
+    if not os.path.exists(setting_config_path):
+        setting_config_path = "config/" + setting_config_path
+        if not os.path.exists(setting_config_path):
+            setting_config_path = "../" + setting_config_path
+
+    # read config
+    with open(setting_config_path, "r", encoding="utf-8") as f:
+        setting_config = json.load(f)
+
+    # set workspace parent:根目录
+    if "workspace" in setting_config:
+        setting_config["workspace"]["parent"] = runtime_config["workspace"]
+    else:
+        setting_config["workspace"] = {"parent": runtime_config["workspace"]}
+    setting_config["video"] = opt_dict(runtime_config, "video")
+
+    # merge setting config
+    if "setting" in config:
+        setting_config.update(runtime_config["setting"])
+
+    # webui config
+    if webui:
+        webui_config_path = config["webui"]
+        if not os.path.exists(webui_config_path):
+            webui_config_path = "config/webui/" + webui_config_path
+            if not os.path.exists(webui_config_path):
+                webui_config_path = "../" + webui_config_path
+
+        with open(webui_config_path, "r", encoding="utf-8") as f:
+            webui_config = json.load(f)
+
+        # merge webui config
+        if "webui" in runtime_config:
+            webui_config.update(runtime_config["webui"])
+
+        return webui_config, setting_config
+    return setting_config
+
+
+TAG_MODE_NONE = ""
+
+
+# 工作路径
+class Workspace:
+
+    def __init__(
+        self,
+        root: str,
+        input: str,
+        output: str,
+        input_crop: str,
+        output_crop: str,
+        input_tag: str,
+        input_mask: str,
+        input_crop_mask: str,
+        crop_info: str,
+    ):
+        self.root = root
+        self.input = input
+        self.output = output
+        self.input_crop = input_crop
+        self.output_crop = output_crop
+        self.input_tag = input_tag
+        self.input_mask = input_mask
+        self.input_crop_mask = input_crop_mask
+        self.crop_info = crop_info
+
+
+# 定义一个倍数函数
+def round_up(num, mul):
+    return (num // mul + 1) * mul
+
+
+class SettingConfig:
+
+    def __init__(self, config: dict, workParent):
+        self.config = config
+        self.webui_work_api = None
+        self.workParent = workParent
+
+    def to_dict(self):
+        return self.__dict__
+
+    def get_tag_mode(self):
+        tag_cfg = opt_dict(self.config, "tag")
+        return opt_dict(tag_cfg, "mode", TAG_MODE_NONE)
+
+    def get_tag_actions(self):
+        tag_cfg = opt_dict(self.config, "tag")
+        return opt_dict(tag_cfg, "actions", [])
+
+    def get_workspace_config(self) -> Workspace:
+        workspace_config = opt_dict(self.config, "workspace")
+        tmp_config = opt_dict(workspace_config, "tmp")
+
+        input = opt_dict(workspace_config, "input", "input")
+        output = opt_dict(workspace_config, "output", "output")
+        workspace_parent = self.workParent
+
+        tmp_parent = opt_dict(tmp_config, "parent", "tmp")
+        input_crop = opt_dict(tmp_config, "input_crop", "input_crop")
+        output_crop = opt_dict(tmp_config, "output_crop", "output_crop")
+        input_tag = opt_dict(tmp_config, "input_tag", "input_crop")
+        input_mask = opt_dict(tmp_config, "input_mask", "input_mask")
+        input_crop_mask = opt_dict(tmp_config, "input_crop_mask", "input_crop_mask")
+        crop_info = opt_dict(tmp_config, "crop_info", "crop_info.txt")
+
+        tmp_path = os.path.join(workspace_parent, tmp_parent)
+
+        return Workspace(
+            workspace_parent,
+            os.path.join(workspace_parent, input),
+            os.path.join(workspace_parent, output),
+            os.path.join(tmp_path, input_crop),
+            os.path.join(tmp_path, output_crop),
+            os.path.join(tmp_path, input_tag),
+            os.path.join(tmp_path, input_mask),
+            os.path.join(tmp_path, input_crop_mask),
+            os.path.join(tmp_path, crop_info),
+        )
+
+    def enable_tag(self):
+        tag_cfg = opt_dict(self.config, "tag")
+        return opt_dict(tag_cfg, "enable", True)

resources/scripts/localWhisper/shotSplit.py

@@ -0,0 +1,307 @@
+# pip install scenedetect opencv-python -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+from scenedetect.video_manager import VideoManager
+from scenedetect.scene_manager import SceneManager
+from scenedetect.stats_manager import StatsManager
+from scenedetect.detectors.content_detector import ContentDetector
+import os
+import sys
+import json
+import subprocess
+from huggingface_hub import hf_hub_download
+from faster_whisper import WhisperModel
+from pathlib import Path
+import public_tools
+
+# 获取智能画面分割的时间或者秒数
+def find_scenes(video_path, sensitivity):
+    print(
+        "正在计算分镜数据" + "sensitivity：" + str(sensitivity) + "path : " + video_path
+    )
+    sys.stdout.flush()
+    video_manager = VideoManager([video_path])
+    stats_manager = StatsManager()
+    scene_manager = SceneManager(stats_manager)
+
+    # 使用contect-detector
+    scene_manager.add_detector(ContentDetector(threshold=float(sensitivity)))
+
+    shijian_list = []
+
+    try:
+        video_manager.set_downscale_factor()
+        video_manager.start()
+        scene_manager.detect_scenes(frame_source=video_manager)
+        scene_list = scene_manager.get_scene_list()
+        print("分镜数据列表：")
+        sys.stdout.flush()
+        for i, scene in enumerate(scene_list):
+            shijian_list.append([scene[0].get_timecode(), scene[1].get_timecode()])
+            print(
+                "Scene %2d: Start %s / Frame %d, End %s / Frame %d"
+                % (
+                    i + 1,
+                    scene[0].get_timecode(),
+                    scene[0].get_frames(),
+                    scene[1].get_timecode(),
+                    scene[1].get_frames(),
+                )
+            )
+            sys.stdout.flush()
+    finally:
+        video_manager.release()
+
+    return shijian_list
+
+
+# 如果不存在就创建
+def createDir(file_dir):
+    # 如果不存在文件夹，就创建
+    if not os.path.isdir(file_dir):
+        os.mkdir(file_dir)
+
+
+# 切分一个视频
+def ClipVideo(video_path, out_folder, image_out_folder, sensitivity, gpu_type):
+    shijian_list = find_scenes(video_path, sensitivity)  # 多组时间列表
+    shijian_list_len = len(shijian_list)
+
+    print("总共有%s个场景" % str(shijian_list_len))
+    sys.stdout.flush()
+    video_list = []
+    for i in range(0, shijian_list_len):
+        start_time_str = shijian_list[i][0]
+        end_time_str = shijian_list[i][1]
+
+        print("开始输出第" + str(i + 1) + "个分镜")
+        video_name = "{:05d}".format(i + 1)
+        out_video_file = os.path.join(out_folder, video_name + ".mp4")
+        sys.stdout.flush()
+        video_list.append(
+            {
+                "start_time_str": start_time_str,
+                "end_time_str": end_time_str,
+                "out_video_file": out_video_file,
+                "video_name": video_name,
+            }
+        )
+
+        # 使用 ffmpeg 裁剪视频
+        command = []
+        command.append("ffmpeg")
+        command.append("-i")
+        command.append(video_path)
+        command.append("-ss")
+        command.append(start_time_str)
+        command.append("-to")
+        command.append(end_time_str)
+        command.append("-c:v")
+
+        if gpu_type == "NVIDIA":
+            command.append("h264_nvenc")
+        elif gpu_type == "AMD":
+            command.append("h264_amf")
+        else:
+            command.append("libx264")
+
+        command.append("-preset")
+        command.append("fast")
+        command.append("-c:a")
+        command.append("copy")
+        command.append(out_video_file)
+        command.append("-loglevel")
+        command.append("error")
+
+        subprocess.run(
+            command,
+            check=True,
+            stderr=subprocess.PIPE,
+        )
+
+    print("分镜输出完成。开始抽帧")
+    sys.stdout.flush()
+    for vi in video_list:
+        h, m, s = vi["start_time_str"].split(":")
+        start_seconds = int(h) * 3600 + int(m) * 60 + float(s)
+
+        h, m, s = vi["end_time_str"].split(":")
+        end_seconds = int(h) * 3600 + int(m) * 60 + float(s)
+        print("正在抽帧：" + vi["video_name"])
+        sys.stdout.flush()
+        subprocess.run(
+            [
+                "ffmpeg",
+                "-ss",
+                str((end_seconds - start_seconds) / 2),
+                "-i",
+                vi["out_video_file"],
+                "-frames:v",
+                "1",
+                os.path.join(image_out_folder, vi["video_name"] + ".png"),
+                "-loglevel",
+                "error",
+            ]
+        )
+
+    print("抽帧完成，开始识别文案")
+    sys.stdout.flush()
+    return video_list
+
+
+def SplitAudio(video_out_folder, video_list):
+    # ffmpeg -i input_file.mp4 -vn -ab 128k output_file.mp3
+    print("正在分离音频!!")
+    mp3_list = []
+    sys.stdout.flush()
+    for v in video_list:
+        mp3_path = os.path.join(video_out_folder, v["video_name"] + ".mp3")
+        mp3_list.append(mp3_path)
+        subprocess.run(
+            [
+                "ffmpeg",
+                "-i",
+                v["out_video_file"],
+                "-vn",
+                "-ab",
+                "128k",
+                mp3_path,
+                "-loglevel",
+                "error",
+            ],
+            check=True,
+        )
+    return mp3_list
+
+
+def GetText(out_folder, mp3_list):
+    text = []
+    # 先获取模型
+    print("正在下载或加载模型")
+    sys.stdout.flush()
+    model_path = Path(
+        hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="preprocessor_config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="tokenizer.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="vocabulary.json",
+    )
+    model = WhisperModel(
+        model_size_or_path=os.path.dirname(model_path),
+        device="auto",
+        local_files_only=True,
+    )
+    print("模型加载成功，开始识别")
+    sys.stdout.flush()
+    for mp in mp3_list:
+        segments, info = model.transcribe(
+            mp,
+            beam_size=5,
+            language="zh",
+            vad_filter=True,
+            vad_parameters=dict(min_silence_duration_ms=1000),
+        )
+        tmp_text = ""
+        for segment in segments:
+            tmp_text += segment.text + "。"
+        print(mp + "识别完成")
+        sys.stdout.flush()
+        text.append(tmp_text)
+
+    # 数据写出
+    print("文本全部识别成功，正在写出")
+    sys.stdout.flush()
+    tools = public_tools.PublicTools()
+    tools.write_to_file(text, os.path.join(out_folder, "文案.txt"))
+    print("写出完成")
+    sys.stdout.flush()
+
+
+def GetTextTask(out_folder, mp, name):
+    text = []
+    # 先获取模型
+    print("正在下载或加载模型")
+    sys.stdout.flush()
+    model_path = Path(
+        hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="preprocessor_config.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="tokenizer.json",
+    )
+    hf_hub_download(
+        repo_id="Systran/faster-whisper-large-v3",
+        filename="vocabulary.json",
+    )
+    model = WhisperModel(
+        model_size_or_path=os.path.dirname(model_path),
+        device="auto",
+        local_files_only=True,
+    )
+    print("模型加载成功，开始识别")
+    sys.stdout.flush()
+    segments, info = model.transcribe(
+        mp,
+        beam_size=5,
+        language="zh",
+        vad_filter=True,
+        vad_parameters=dict(min_silence_duration_ms=1000),
+    )
+    tmp_text = ""
+    for segment in segments:
+        tmp_text += segment.text + "。"
+    print(mp + "识别完成")
+    sys.stdout.flush()
+    text.append(tmp_text)
+
+    # 数据写出
+    sys.stdout.flush()
+    tools = public_tools.PublicTools()
+    tools.write_to_file(text, os.path.join(out_folder, name + ".txt"))
+    sys.stdout.flush()
+
+
+def get_fram(video_path, out_path, sensitivity):
+    try:
+        shijian_list = find_scenes(video_path, sensitivity)  # 多组时间列表
+        print("总共有%s个场景" % str(len(shijian_list)))
+        print("开始输出json")
+        print(shijian_list)
+        # 将数组中的消息写道json文件中
+        with open(out_path, "w") as file:
+            # 将数组写入到指定的json文件
+            json.dump(shijian_list, file)
+        print("输出完成")
+    except Exception as e:
+        print("出现错误" + str(e))
+        exit(0)
+
+
+def init(video_path, video_out_folder, image_out_folder, sensitivity, gpu_type):
+    v_l = ClipVideo(
+        video_path, video_out_folder, image_out_folder, sensitivity, gpu_type
+    )
+
+    # 开始分离音频
+    m_l = SplitAudio(video_out_folder, v_l)
+    # 开始识别字幕
+    GetText(os.path.dirname(video_out_folder), m_l)

resources/scripts/requirements.txt

@@ -1,298 +0,0 @@
-accelerate==0.30.1
-addict==2.4.0
-aiofiles==23.2.1
-aiohttp==3.8.6
-aiosignal==1.3.1
-alibabacloud-bailian20230601==1.6.1
-alibabacloud-credentials==0.3.3
-alibabacloud-endpoint-util==0.0.3
-alibabacloud-gateway-spi==0.0.1
-alibabacloud-openapi-util==0.2.2
-alibabacloud-tea==0.3.6
-alibabacloud-tea-openapi==0.3.9
-alibabacloud-tea-util==0.3.12
-alibabacloud-tea-xml==0.0.2
-aliyun-python-sdk-core==2.15.0
-aliyun-python-sdk-kms==2.16.2
-altair==5.3.0
-altgraph==0.17.4
-annotated-types==0.6.0
-anthropic==0.26.1
-antlr4-python3-runtime==4.9.3
-anyio==4.3.0
-APScheduler==3.10.4
-arxiv==2.1.0
-astor==0.8.1
-asttokens==2.4.1
-async-timeout==4.0.3
-attrdict==2.0.1
-attrs==23.2.0
-av==11.0.0
-azure-cognitiveservices-speech==1.37.0
-Babel==2.15.0
-backports.tarfile==1.1.1
-baidu-aip==4.16.13
-bce-python-sdk==0.9.11
-beautifulsoup4==4.12.3
-bidict==0.23.1
-blinker==1.8.2
-broadscope-bailian==1.3.1
-cachetools==5.3.3
-certifi==2024.2.2
-cffi==1.16.0
-cfgv==3.4.0
-chardet==5.2.0
-charset-normalizer==3.3.2
-chatgpt-tool-hub==0.5.0
-cheroot==10.0.1
-click==8.1.7
-colorama==0.4.6
-coloredlogs==15.0.1
-comtypes==1.4.2
-contourpy==1.2.1
-controlnet-aux==0.0.3
-crcmod==1.7
-cryptography==42.0.5
-cssselect==1.2.0
-cssutils==2.11.0
-ctranslate2==4.1.0
-curl_cffi==0.6.4
-cx-Logging==3.1.0
-cx_Freeze==6.15.16
-cycler==0.12.1
-Cython==3.0.10
-dashscope==1.19.2
-datasets==2.18.0
-decorator==4.4.2
-diffusers==0.27.2
-dill==0.3.8
-dingtalk-stream==0.18.1
-distlib==0.3.8
-distro==1.9.0
-dnspython==2.6.1
-dulwich==0.22.1
-easydict==1.13
-edge-tts==6.1.12
-einops==0.7.0
-elevenlabs==1.0.3
-email_validator==2.1.1
-et-xmlfile==1.1.0
-exceptiongroup==1.2.1
-executing==2.0.1
-fastapi==0.108.0
-fastapi-cli==0.0.2
-faster-whisper==1.0.1
-feedparser==6.0.10
-ffmpy==0.3.2
-filelock==3.13.1
-fire==0.6.0
-Flask==3.0.3
-flask-babel==4.0.0
-flatbuffers==24.3.7
-fonttools==4.53.0
-frozenlist==1.4.1
-fsspec==2024.2.0
-future==1.0.0
-gast==0.5.4
-google-ai-generativelanguage==0.6.4
-google-api-core==2.19.0
-google-api-python-client==2.130.0
-google-auth==2.29.0
-google-auth-httplib2==0.2.0
-google-generativeai==0.5.4
-googleapis-common-protos==1.63.0
-gradio==4.21.0
-gradio_client==0.12.0
-grpcio==1.64.0
-grpcio-status==1.62.2
-gTTS==2.5.1
-h11==0.14.0
-HTMLParser==0.0.2
-httpcore==1.0.5
-httplib2==0.22.0
-httptools==0.6.1
-httpx==0.27.0
-huggingface-hub==0.23.2
-humanfriendly==10.0
-identify==2.5.36
-idna==3.6
-imageio==2.34.0
-imageio-ffmpeg==0.4.9
-imgaug==0.4.0
-importlib_metadata==7.0.2
-importlib_resources==6.4.0
-install==1.3.5
-IOPaint==1.3.3
-ipython==8.24.0
-itsdangerous==2.2.0
-jaraco.context==5.3.0
-jaraco.functools==4.0.1
-jedi==0.19.1
-Jinja2==3.1.3
-jiter==0.4.0
-jmespath==0.10.0
-jsonschema==4.22.0
-jsonschema-specifications==2023.12.1
-kiwisolver==1.4.5
-langid==1.1.6
-lazy_loader==0.4
-lief==0.14.1
-linkai==0.0.6.0
-lmdb==1.4.1
-loguru==0.7.2
-lxml==5.2.2
-markdown-it-py==3.0.0
-MarkupSafe==2.1.5
-matplotlib==3.9.0
-matplotlib-inline==0.1.7
-mdurl==0.1.2
-modelscope==1.13.1
-more-itertools==10.2.0
-moviepy==1.0.3
-mpmath==1.3.0
-multidict==6.0.5
-multiprocess==0.70.16
-networkx==3.2.1
-nodeenv==1.8.0
-Nuitka==2.1.2
-numpy==1.24.2
-omegaconf==2.3.0
-onnxruntime==1.17.1
-openai==0.27.8
-opencv-contrib-python==4.6.0.66
-opencv-python==4.6.0.66
-opencv-python-headless==4.9.0.80
-openpyxl==3.1.2
-opt-einsum==3.3.0
-optionaldict==0.1.2
-ordered-set==4.1.0
-orjson==3.10.3
-oss2==2.18.4
-packaging==24.0
-paddleocr==2.7.3
-paddlepaddle==2.6.1
-pandas==2.2.1
-parso==0.8.4
-pdf2docx==0.5.8
-pefile==2023.2.7
-peft==0.7.1
-piexif==1.1.3
-pillow==10.3.0
-platformdirs==4.2.0
-pre-commit==3.7.1
-premailer==3.10.0
-proglog==0.1.10
-prompt-toolkit==3.0.43
-proto-plus==1.23.0
-protobuf==3.20.2
-psutil==5.9.8
-pure-eval==0.2.2
-pyarrow==15.0.1
-pyarrow-hotfix==0.6
-pyasn1==0.6.0
-pyasn1_modules==0.4.0
-pyclipper==1.3.0.post5
-pycparser==2.21
-pycryptodome==3.20.0
-pydantic==2.5.3
-pydantic_core==2.14.6
-pydub==0.25.1
-Pygments==2.18.0
-pyinstaller==6.5.0
-pyinstaller-hooks-contrib==2024.3
-PyJWT==2.8.0
-PyMuPDF==1.24.5
-PyMuPDFb==1.24.3
-pyOpenSSL==24.1.0
-pyoxidizer==0.24.0
-pyparsing==3.1.2
-pypiwin32==223
-pypng==0.20220715.0
-PyQRCode==1.2.1
-pyreadline3==3.4.1
-pytesseract==0.3.10
-python-dateutil==2.9.0.post0
-python-docx==1.1.2
-python-dotenv==1.0.1
-python-engineio==4.9.1
-python-multipart==0.0.9
-python-socketio==5.7.2
-pyttsx3==2.90
-pytz==2024.1
-pywin32==306
-pywin32-ctypes==0.2.2
-PyYAML==6.0.1
-qrcode==7.4.2
-rapidfuzz==3.9.3
-rarfile==4.2
-referencing==0.35.1
-regex==2024.5.15
-requests==2.31.0
-rich==13.7.1
-rpds-py==0.18.1
-rsa==4.9
-ruff==0.4.7
-safetensors==0.4.3
-scenedetect==0.6.3
-scikit-image==0.23.2
-scipy==1.12.0
-semantic-version==2.10.0
-sgmllib3k==1.0.0
-shapely==2.0.4
-shellingham==1.5.4
-simple-websocket==1.0.0
-simplejson==3.19.2
-six==1.16.0
-sniffio==1.3.1
-sortedcontainers==2.4.0
-soupsieve==2.5
-SpeechRecognition==3.10.4
-stack-data==0.6.3
-starlette==0.32.0.post1
-sympy==1.12
-tenacity==8.2.3
-termcolor==2.4.0
-tifffile==2024.5.22
-tiktoken==0.4.0
-timm==1.0.3
-tokenizers==0.19.1
-tomli==2.0.1
-tomlkit==0.12.0
-toolz==0.12.1
-torch==2.1.2+cu118
-torchvision==0.16.2+cu118
-tqdm==4.66.2
-traitlets==5.14.3
-transformers==4.41.2
-typer==0.12.3
-typer-config==1.4.0
-typing_extensions==4.10.0
-tzdata==2024.1
-tzlocal==5.2
-ujson==5.9.0
-uritemplate==4.1.1
-urllib3==2.2.1
-utility==1.0
-uvicorn==0.29.0
-virtualenv==20.26.2
-visualdl==2.5.3
-watchfiles==0.21.0
-wcwidth==0.2.13
-web.py==0.62
-websocket-client==1.2.0
-websockets==11.0.3
-wechatpy==1.8.18
-Werkzeug==3.0.3
-wikipedia==1.4.0
-win32-setctime==1.1.0
-wolframalpha==5.0.0
-wsproto==1.2.0
-xlrd==2.0.1
-xmltodict==0.13.0
-xxhash==3.4.1
-yacs==0.1.8
-yapf==0.40.2
-yarl==1.9.4
-zhipuai==2.1.0.20240521
-zipp==3.18.1
-zstandard==0.22.0

resources/scripts/shotSplit.py

@@ -8,8 +8,8 @@ import os
 import sys
 import json
 import subprocess
-from huggingface_hub import hf_hub_download
+# from huggingface_hub import hf_hub_download
-from faster_whisper import WhisperModel
+# from faster_whisper import WhisperModel
 import public_tools
 from pathlib import Path
 
@@ -174,111 +174,111 @@ def SplitAudio(video_out_folder, video_list):
     return mp3_list
 
 
-def GetText(out_folder, mp3_list):
+# def GetText(out_folder, mp3_list):
-    text = []
+    # text = []
-    # 先获取模型
+    # # 先获取模型
-    print("正在下载或加载模型")
+    # print("正在下载或加载模型")
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    model_path = Path(
+    # model_path = Path(
-        hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
+    #     hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="config.json",
+    #     filename="config.json",
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="preprocessor_config.json",
+    #     filename="preprocessor_config.json",
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="tokenizer.json",
+    #     filename="tokenizer.json",
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="vocabulary.json",
+    #     filename="vocabulary.json",
-    )
+    # )
-    model = WhisperModel(
+    # model = WhisperModel(
-        model_size_or_path=os.path.dirname(model_path),
+    #     model_size_or_path=os.path.dirname(model_path),
-        device="auto",
+    #     device="auto",
-        local_files_only=True,
+    #     local_files_only=True,
-    )
+    # )
-    print("模型加载成功，开始识别")
+    # print("模型加载成功，开始识别")
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    for mp in mp3_list:
+    # for mp in mp3_list:
-        segments, info = model.transcribe(
+    #     segments, info = model.transcribe(
-            mp,
+    #         mp,
-            beam_size=5,
+    #         beam_size=5,
-            language="zh",
+    #         language="zh",
-            vad_filter=True,
+    #         vad_filter=True,
-            vad_parameters=dict(min_silence_duration_ms=1000),
+    #         vad_parameters=dict(min_silence_duration_ms=1000),
-        )
+    #     )
-        tmp_text = ""
+    #     tmp_text = ""
-        for segment in segments:
+    #     for segment in segments:
-            tmp_text += segment.text + "。"
+    #         tmp_text += segment.text + "。"
-        print(mp + "识别完成")
+    #     print(mp + "识别完成")
-        sys.stdout.flush()
+    #     sys.stdout.flush()
-        text.append(tmp_text)
+    #     text.append(tmp_text)
 
-    # 数据写出
+    # # 数据写出
-    print("文本全部识别成功，正在写出")
+    # print("文本全部识别成功，正在写出")
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    tools = public_tools.PublicTools()
+    # tools = public_tools.PublicTools()
-    tools.write_to_file(text, os.path.join(out_folder, "文案.txt"))
+    # tools.write_to_file(text, os.path.join(out_folder, "文案.txt"))
-    print("写出完成")
+    # print("写出完成")
-    sys.stdout.flush()
+    # sys.stdout.flush()
 
 
-def GetTextTask(out_folder, mp, name):
+# def GetTextTask(out_folder, mp, name):
-    text = []
+    # text = []
-    # 先获取模型
+    # # 先获取模型
-    print("正在下载或加载模型")
+    # print("正在下载或加载模型")
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    model_path = Path(
+    # model_path = Path(
-        hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
+    #     hf_hub_download(repo_id="Systran/faster-whisper-large-v3", filename="model.bin")
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="config.json",
+    #     filename="config.json",
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="preprocessor_config.json",
+    #     filename="preprocessor_config.json",
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="tokenizer.json",
+    #     filename="tokenizer.json",
-    )
+    # )
-    hf_hub_download(
+    # hf_hub_download(
-        repo_id="Systran/faster-whisper-large-v3",
+    #     repo_id="Systran/faster-whisper-large-v3",
-        filename="vocabulary.json",
+    #     filename="vocabulary.json",
-    )
+    # )
-    model = WhisperModel(
+    # model = WhisperModel(
-        model_size_or_path=os.path.dirname(model_path),
+    #     model_size_or_path=os.path.dirname(model_path),
-        device="auto",
+    #     device="auto",
-        local_files_only=True,
+    #     local_files_only=True,
-    )
+    # )
-    print("模型加载成功，开始识别")
+    # print("模型加载成功，开始识别")
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    segments, info = model.transcribe(
+    # segments, info = model.transcribe(
-        mp,
+    #     mp,
-        beam_size=5,
+    #     beam_size=5,
-        language="zh",
+    #     language="zh",
-        vad_filter=True,
+    #     vad_filter=True,
-        vad_parameters=dict(min_silence_duration_ms=1000),
+    #     vad_parameters=dict(min_silence_duration_ms=1000),
-    )
+    # )
-    tmp_text = ""
+    # tmp_text = ""
-    for segment in segments:
+    # for segment in segments:
-        tmp_text += segment.text + "。"
+    #     tmp_text += segment.text + "。"
-    print(mp + "识别完成")
+    # print(mp + "识别完成")
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    text.append(tmp_text)
+    # text.append(tmp_text)
 
-    # 数据写出
+    # # 数据写出
-    sys.stdout.flush()
+    # sys.stdout.flush()
-    tools = public_tools.PublicTools()
+    # tools = public_tools.PublicTools()
-    tools.write_to_file(text, os.path.join(out_folder, name + ".txt"))
+    # tools.write_to_file(text, os.path.join(out_folder, name + ".txt"))
-    sys.stdout.flush()
+    # sys.stdout.flush()
 
 
 def get_fram(video_path, out_path, sensitivity):
@@ -297,12 +297,12 @@ def get_fram(video_path, out_path, sensitivity):
         exit(0)
 
 
-def init(video_path, video_out_folder, image_out_folder, sensitivity, gpu_type):
+# def init(video_path, video_out_folder, image_out_folder, sensitivity, gpu_type):
-    v_l = ClipVideo(
+#     v_l = ClipVideo(
-        video_path, video_out_folder, image_out_folder, sensitivity, gpu_type
+#         video_path, video_out_folder, image_out_folder, sensitivity, gpu_type
-    )
+#     )
 
-    # 开始分离音频
+#     # 开始分离音频
-    m_l = SplitAudio(video_out_folder, v_l)
+#     m_l = SplitAudio(video_out_folder, v_l)
-    # 开始识别字幕
+#     # 开始识别字幕
-    GetText(os.path.dirname(video_out_folder), m_l)
+#     GetText(os.path.dirname(video_out_folder), m_l)

src/main/Service/Book/ReverseBook.ts

@@ -8,7 +8,7 @@ import { DEFINE_STRING } from "../../../define/define_string";
 import path from 'path'
 import { BasicReverse } from './basicReverse'
 import { BookTaskDetailService } from '../../../define/db/service/Book/bookTaskDetailService'
-import { TaskScheduler } from "../task/taskScheduler"
+import { LogScheduler } from "../task/logScheduler"
 import { Book } from '../../../model/book'
 import { LoggerStatus, OtherData, ResponseMessageType } from '../../../define/enum/softwareEnum'
 import { GeneralResponse } from '../../../model/generalResponse'
@@ -28,7 +28,7 @@ import { isEmpty } from 'lodash'
  */
 export class ReverseBook {
   basicReverse: BasicReverse
-  taskScheduler: TaskScheduler
+  logScheduler: LogScheduler
   mjOpt: MJOpt = new MJOpt()
   sdOpt: SDOpt = new SDOpt()
   tagDefine: TagDefine
@@ -42,7 +42,7 @@ export class ReverseBook {
     this.tagDefine = new TagDefine()
     this.subtitle = new Subtitle()
     this.watermark = new Watermark()
-    this.taskScheduler = new TaskScheduler()
+    this.logScheduler = new LogScheduler()
     this.bookServiceBasic = new BookServiceBasic()
     this.bookBasic = new BookBasic()
   }
@@ -301,7 +301,7 @@ export class ReverseBook {
         await this.bookServiceBasic.AddBookBackTask(book.id, task_type, TaskExecuteType.AUTO, bookTaskDetail.bookTaskId, bookTaskDetail.id, DEFINE_STRING.BOOK.REVERSE_PROMPT_RETURN
         );
         // 添加返回日志
-        await this.taskScheduler.AddLogToDB(book.id, book.type, `添加 ${task_type} 反推任务成功`, bookTaskDetail.bookTaskId, LoggerStatus.SUCCESS)
+        await this.logScheduler.AddLogToDB(book.id, book.type, `添加 ${task_type} 反推任务成功`, bookTaskDetail.bookTaskId, LoggerStatus.SUCCESS)
       }
     } catch (error) {
       throw error

src/main/Service/Book/basicReverse.ts

@@ -5,7 +5,7 @@ const { exec } = require('child_process')
 const execAsync = util.promisify(exec)
 import { define } from '../../../define/define'
 import { BookService } from '../../../define/db/service/Book/bookService'
-import { TaskScheduler } from '../task/taskScheduler'
+import { LogScheduler } from '../task/logScheduler'
 import { LoggerStatus, LoggerType, OtherData } from '../../../define/enum/softwareEnum'
 import { errorMessage, successMessage } from '../../Public/generalTools'
 import { CheckFileOrDirExist, CheckFolderExistsOrCreate } from '../../../define/Tools/file'
@@ -35,11 +35,11 @@ export class BasicReverse {
   bookTaskDetailService: BookTaskDetailService
   bookBackTaskListService: BookBackTaskListService
 
-  taskScheduler: TaskScheduler
+  logScheduler: LogScheduler
   ffmpegOptions: FfmpegOptions
 
   constructor() {
-    this.taskScheduler = new TaskScheduler()
+    this.logScheduler = new LogScheduler()
     this.ffmpegOptions = new FfmpegOptions()
   }
 
@@ -109,7 +109,7 @@ export class BasicReverse {
       if (taskRes.code == 0) {
         throw new Error(taskRes.message)
       }
-      this.taskScheduler.AddLogToDB(
+      this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         `添加分镜任务成功`,
@@ -149,7 +149,7 @@ export class BasicReverse {
     let sensitivity = 30
     // 开始之前，推送日志
     let log_content = `开始进行分镜操作，视频地址：${oldVideoPath}，敏感度：${sensitivity}，正在调用程序进行处理`
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       bookId,
       book.type,
       log_content,
@@ -170,7 +170,7 @@ export class BasicReverse {
     // 有错误输出
     if (output.stderr != '') {
       let error_msg = `分镜成功，但有警告提示：${output.stderr}`
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         error_msg,
@@ -187,7 +187,7 @@ export class BasicReverse {
         BookTaskStatus.STORYBOARD_FAIL,
         error_message
       )
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         error_message,
@@ -205,7 +205,7 @@ export class BasicReverse {
         BookTaskStatus.STORYBOARD_FAIL,
         error_msg
       )
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         error_msg,
@@ -237,7 +237,7 @@ export class BasicReverse {
 
     this.bookTaskService.UpdateBookTaskStatus(bookTaskId, BookTaskStatus.STORYBOARD_DONE)
     // 分镜成功，推送日志
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       bookId,
       book.type,
       `分镜成功，分镜数据如下：${frameJsonData}`,
@@ -310,7 +310,7 @@ export class BasicReverse {
 
       if (bookTaskDetail.data.length <= 0) {
         // 传入的分镜数据为空，需要重新获取
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           bookId,
           book.type,
           `没有传入分镜数据，开始调用分镜方法`,
@@ -339,7 +339,7 @@ export class BasicReverse {
 
       this.bookTaskService.UpdateBookTaskStatus(bookTask.id, BookTaskStatus.SPLIT)
       // 有分镜数据，开始处理
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         `成功获取分镜数据，开始添加裁剪视频任务`,
@@ -363,7 +363,7 @@ export class BasicReverse {
         }
       }
       // 添加日志
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         `添加视频裁剪任务成功`,
@@ -424,7 +424,7 @@ export class BasicReverse {
     // 小改小说批次的状态
     this.bookTaskService.UpdateBookTaskStatus(bookTaskDetail.bookTaskId, BookTaskStatus.SPLIT_DONE)
     // 结束，分镜完毕，推送日志，返回成功
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       bookTaskDetail.bookId,
       book.type,
       `${bookTaskDetail.name}_视频裁剪完成`,
@@ -490,7 +490,7 @@ export class BasicReverse {
         })
       }
       if (bookTaskRes.data.bookTasks.length <= 0 || bookTaskRes.data.total <= 0) {
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           bookId,
           book.type,
           `没有找到对应的小说批次任务数据，请检查bookId是否正确`,
@@ -508,7 +508,7 @@ export class BasicReverse {
         bookTaskId: bookTask.id
       })
       if (bookTaskDetails.data.length <= 0) {
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           bookId,
           book.type,
           `没有找到对应的小说批次任务数据，请检查bookId是否正确，或者手动执行`,
@@ -531,7 +531,7 @@ export class BasicReverse {
           throw new Error(taskRes.message)
         }
         // 添加日志
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           bookId,
           book.type,
           `添加音频 ${taskRes.data.name} 分离任务成功`,
@@ -588,7 +588,7 @@ export class BasicReverse {
       })
 
       // 推送成功消息
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         task.bookId,
         book.type,
         `${bookTaskDetail.name}分离音频成功，输出地址：${audioPath}`,
@@ -656,7 +656,7 @@ export class BasicReverse {
           throw new Error(taskRes.message)
         }
 
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           bookId,
           book.type,
           `添加 ${taskRes.data.name} 抽帧任务成功`,
@@ -701,7 +701,7 @@ export class BasicReverse {
     })
 
     // 推送成功消息
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       book.id,
       book.type,
       `${bookTaskDetail.name}抽帧成功，输出地址：${outputFramePath}`,
@@ -797,7 +797,7 @@ export class BasicReverse {
         }
       }
 
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         `添加提取字幕任务成功`,
@@ -821,9 +821,9 @@ export class BasicReverse {
     // 判断是不是用本地的wisper服务
     if (isWisper) {
       // 开始调用wisper
-      // 使用异步的方法调用一个python程序，然后写入到指定的json文件中k
+      // 使用异步的方法调用一个python程序，然后写入到指定的json文件中
       let out_dir = path.dirname(bookTaskDetail.videoPath)
-
+      // #TODO -t 被移除
       let command = `"${path.join(define.scripts_path, 'Lai.exe')}" "-t" "${out_dir}" "${bookTaskDetail.audioPath
         }" "${bookTaskDetail.name}"`
       const output = await execAsync(command, {
@@ -833,7 +833,7 @@ export class BasicReverse {
       // 有错误输出
       if (output.stderr != '') {
         let error_msg = `提取字幕成功，但有警告提示：${output.stderr}`
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           book.id,
           book.type,
           error_msg,
@@ -856,7 +856,7 @@ export class BasicReverse {
     })
 
     // 提取字幕成功，推送日志
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       book.id,
       book.type,
       `${bookTaskDetail.name} 提取字幕成功`,

src/main/Service/Book/bookFrame.ts

@@ -7,7 +7,7 @@ import { FfmpegOptions } from "../ffmpegOptions";
 import { CheckFileOrDirExist, CopyFileOrFolder, DeleteFolderAllFile } from "../../../define/Tools/file";
 import fs from 'fs';
 import { Book } from "../../../model/book";
-import { TaskScheduler } from '../task/taskScheduler';
+import { LogScheduler } from '../task/logScheduler';
 import { BookBasic } from "./BooKBasic";
 import { LoggerStatus, OtherData } from "../../../define/enum/softwareEnum";
 import { BasicReverse } from "./basicReverse";
@@ -15,18 +15,17 @@ import { BasicReverse } from "./basicReverse";
 export class BookFrame {
   bookServiceBasic: BookServiceBasic
   ffmpegOptions: FfmpegOptions
-  taskScheduler: TaskScheduler
+  logScheduler: LogScheduler
   basicReverse: BasicReverse
   bookBasic: BookBasic
   constructor() {
     this.bookServiceBasic = new BookServiceBasic();
     this.ffmpegOptions = new FfmpegOptions();
-    this.taskScheduler = new TaskScheduler()
+    this.logScheduler = new LogScheduler()
     this.bookBasic = new BookBasic()
     this.basicReverse = new BasicReverse()
   }
 
-
   /**
    * 替换指定分镜的视频当前帧
    * @param bookTaskDetailId 指定的小说分镜ID
@@ -138,7 +137,7 @@ export class BookFrame {
         })
       } catch (error) {
         // 传入的分镜数据为空，需要重新获取
-        await this.taskScheduler.AddLogToDB(
+        await this.logScheduler.AddLogToDB(
           bookId,
           book.type,
           `没有传入分镜数据，请先进行分镜计算`,
@@ -164,7 +163,7 @@ export class BookFrame {
         }
         let res = await this.basicReverse.FrameDataToCutVideoData(item, shortClipData[i]);
       }
-      await this.taskScheduler.AddLogToDB(
+      await this.logScheduler.AddLogToDB(
         bookId,
         book.type,
         "所有的视频裁剪完成，开始抽帧",

src/main/Service/Book/bookVideo.ts

@@ -173,6 +173,12 @@ export class BookVideo {
   }
 
 
+  /**
+   * 添加剪映草稿
+   * @param id 
+   * @param operateBookType 
+   * @returns 
+   */
   async AddJianyingDraft(id: string, operateBookType: OperateBookType): Promise<GeneralResponse.ErrorItem | GeneralResponse.SuccessItem> {
     try {
       await this.InitService();

src/main/Service/MJ/mj.ts

@@ -13,7 +13,7 @@ import { MJSetting } from "../../../model/Setting/mjSetting";
 import { GeneralResponse } from "../../../model/generalResponse"
 import { LoggerStatus, ResponseMessageType } from "../../../define/enum/softwareEnum";
 import { ImageStyle } from "../Book/imageStyle";
-import { TaskScheduler } from "../task/taskScheduler";
+import { LogScheduler } from "../task/logScheduler";
 import { Tools } from "../../../main/tools"
 import { BookServiceBasic } from "../ServiceBasic/bookServiceBasic";
 import { PresetService } from "../presetService";
@@ -28,14 +28,14 @@ export class MJOpt {
   mjApi: MJApi;
   mjSetting: MJSetting.MjSetting
   imageStyle: ImageStyle;
-  taskScheduler: TaskScheduler;
+  logScheduler: LogScheduler;
   tools: Tools;
   bookServiceBasic: BookServiceBasic
   presetService: PresetService
   softWareServiceBasic: SoftWareServiceBasic
   constructor() {
     this.imageStyle = new ImageStyle()
-    this.taskScheduler = new TaskScheduler()
+    this.logScheduler = new LogScheduler()
     this.tools = new Tools()
     this.bookServiceBasic = new BookServiceBasic();
     this.presetService = new PresetService()
@@ -528,7 +528,7 @@ export class MJOpt {
         let taskRes = await this.bookServiceBasic.AddBookBackTask(element.bookId, BookBackTaskType.MJ_IMAGE, TaskExecuteType.AUTO, element.bookTaskId, element.id, responseMessageName
         );
         // 添加返回日志
-        await this.taskScheduler.AddLogToDB(element.bookId, BookBackTaskType.MJ_IMAGE, `添加 ${element.name} MJ生成任务成功`, element.bookTaskId, LoggerStatus.SUCCESS)
+        await this.logScheduler.AddLogToDB(element.bookId, BookBackTaskType.MJ_IMAGE, `添加 ${element.name} MJ生成任务成功`, element.bookTaskId, LoggerStatus.SUCCESS)
       }
       // 全部完毕
       return successMessage(null, "MJ添加生成图片任务成功", "MJOpt_AddGenerateImageTask")

src/main/Service/SD/sd.ts

@@ -48,8 +48,10 @@ export class SDOpt {
       const id = ids[i];
       let scene = await this.presetService.GetScenePresetDetailById(id)
       if (scene.code == 1) {
+        if (scene.data) {
           // 这边开始拼接
           result += scene.data.prompt + ', '
+        }
       } else {
         throw new Error(scene.message)
       }
@@ -68,10 +70,12 @@ export class SDOpt {
       const id = ids[i];
       let character = await this.presetService.GetCharacterPresetDetailById(id)
       if (character.code == 1) {
+        if (character.data) {
           result += character.data.prompt + ', '
           if (character.data.lora && character.data.lora != '无' && character.data.loraWeight) {
             result += `, <lora:${character.data.lora}:${character.data.lora_weight}>`
           }
+        }
       } else {
         throw new Error(character.message)
       }

src/main/Service/ServiceBasic/bookServiceBasic.ts

@@ -69,7 +69,7 @@ class BookServiceBasic {
   GetBookTaskDetailDataById = async (bookTaskDetailId: string) => await this.bookTaskDetailServiceBasic.GetBookTaskDetailDataById(bookTaskDetailId);
   GetBookTaskDetailData = async (condition: Book.QueryBookTaskDetailCondition, returnEmpty: boolean = false) => await this.bookTaskDetailServiceBasic.GetBookTaskDetailData(condition, returnEmpty);
   UpdateBookTaskDetail = async (bookTaskDetailId: string, data: Book.SelectBookTaskDetail) => await this.bookTaskDetailServiceBasic.UpdateBookTaskDetail(bookTaskDetailId, data);
-  UpdateBookTaskStatus = async (bookTaskDetailId: string, status: BookTaskStatus) => await this.bookTaskDetailServiceBasic.UpdateBookTaskStatus(bookTaskDetailId, status);
+  UpdateBookTaskStatus = async (bookTaskDetailId: string, status: BookTaskStatus,errorMsg? : string) => await this.bookTaskDetailServiceBasic.UpdateBookTaskStatus(bookTaskDetailId, status,errorMsg);
   DeleteBookTaskDetailReversePromptById = async (bookTaskDetailId: string, reversePromptId: string) => await this.bookTaskDetailServiceBasic.DeleteBookTaskDetailReversePromptById(bookTaskDetailId);
   DeleteBoookTaskDetailGenerateImage = async (bookTaskDetailId: string) => await this.bookTaskDetailServiceBasic.DeleteBoookTaskDetailGenerateImage(bookTaskDetailId);
   UpdateBookTaskDetailReversePrompt = async (bookTaskDetailId: string, reversePromptId: string, data: Book.ReversePrompt) => await this.bookTaskDetailServiceBasic.UpdateBookTaskDetailReversePrompt(bookTaskDetailId, reversePromptId, data);

src/main/Service/Subtitle/subtitle.ts

@@ -16,7 +16,7 @@ import fs from 'fs'
 import { GeneralResponse } from '../../../model/generalResponse'
 import { BookServiceBasic } from '../ServiceBasic/bookServiceBasic'
 import { LoggerStatus, OtherData, ResponseMessageType } from '../../../define/enum/softwareEnum'
-import { TaskScheduler } from '../task/taskScheduler'
+import { LogScheduler } from '../task/logScheduler'
 import { SubtitleModel } from '../../../model/subtitle'
 import { BookTaskStatus, OperateBookType } from '../../../define/enum/bookEnum'
 import axios from 'axios'
@@ -24,8 +24,9 @@ import { GptService } from '../GPT/gpt'
 import FormData from 'form-data'
 import { RetryWithBackoff } from '../../../define/Tools/common'
 import { DEFINE_STRING } from '../../../define/define_string'
+import { DraftTimeLineJson } from '../jianying/jianyingService'
 const util = require('util')
-const { exec } = require('child_process')
+const { spawn, exec } = require('child_process')
 const execAsync = util.promisify(exec)
 const fspromises = fs.promises
 
@@ -36,12 +37,12 @@ const fspromises = fs.promises
 export class Subtitle {
   ffmpegOptions: FfmpegOptions
   bookServiceBasic: BookServiceBasic
-  taskScheduler: TaskScheduler
+  logScheduler: LogScheduler
   gptService: GptService
 
   constructor() {
     this.bookServiceBasic = new BookServiceBasic()
-    this.taskScheduler = new TaskScheduler()
+    this.logScheduler = new LogScheduler()
     this.ffmpegOptions = new FfmpegOptions()
     this.gptService = new GptService()
   }
@@ -74,28 +75,6 @@ export class Subtitle {
     return frameTimes
   }
 
-  /**
-   * 加载指定的的小说相关的所有的数据
-   * @param bookId 小说ID
-   * @param bookTaskId 小说任务ID
-   * @returns 
-   */
-  async GetBookAllData(bookId: string, bookTaskId: string = null): Promise<{ book: Book.SelectBook, bookTask: Book.SelectBookTask, bookTaskDetails: Book.SelectBookTaskDetail[] }> {
-    let { book, bookTask } = await this.bookServiceBasic.GetBookAndTask(bookId, bookTaskId ? bookTaskId : 'output_00001')
-    if (isEmpty(book.subtitlePosition)) {
-      throw new Error("请先设置小说的字幕位置")
-    }
-    // 获取所有的分镜数据
-    let bookTaskDetails = await this.bookServiceBasic.GetBookTaskDetailData({
-      bookId: bookId,
-      bookTaskId: bookTask.id
-    })
-    if (bookTaskDetails.length <= 0) {
-      throw new Error("没有找到对应的分镜数据，请先执行对应的操作")
-    }
-    return { book, bookTask, bookTaskDetails }
-  }
-
   /**
    * 通用的小说获取分案的返回方法
    * @param content 获取的文案内容
@@ -123,7 +102,7 @@ export class Subtitle {
     }, DEFINE_STRING.BOOK.GET_COPYWRITING_RETURN)
 
     // 添加日志
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       book.id,
       book.type,
       `${bookTaskDetail.name} 识别文案成功`,
@@ -562,7 +541,7 @@ export class Subtitle {
     })
 
     // 推送成功消息
-    await this.taskScheduler.AddLogToDB(
+    await this.logScheduler.AddLogToDB(
       book.id,
       book.type,
       `${bookTaskDetail.name}分离音频成功，输出地址：${audioPath}`,
@@ -667,4 +646,73 @@ export class Subtitle {
     }
   }
   //#endregion
+
+
+  //#region 本地Whisper识别字幕相关操作
+
+  async GetTextByLocalWhisper(frameTimeList: DraftTimeLineJson[], outDir: string, mp3Dir: string, localWhisperPath?: string): Promise<void> {
+    try {
+      let localWhisperPathExePath = localWhisperPath
+      if (isEmpty(localWhisperPathExePath)) {
+        localWhisperPathExePath = path.join(define.scripts_path, 'localWhisper/local_whisper.exe')
+      }
+      return new Promise((resolve, reject) => {
+        let child = spawn(
+          localWhisperPathExePath,
+          ['-ts', outDir, mp3Dir],
+          { encoding: 'utf-8' }
+        );
+        child.on('error', (error) => {
+          console.log('error=', error)
+          this.logScheduler.ReturnLogger(errorMessage("使用localWhisper识别字幕失败输出，失败信息如下：" + error.message))
+          reject(new Error(error.message))
+        })
+        child.stdout.on('data', (data) => {
+          console.log(data.toString())
+          this.logScheduler.ReturnLogger(successMessage(data.toString(), "使用localWhisper识别字幕输出"))
+        })
+        child.stderr.on('data', (data) => {
+          console.log('stderr=', data.toString())
+          this.logScheduler.ReturnLogger(errorMessage("使用localWhisper识别字幕失败输出，失败信息如下：stderr = " + data.toString()))
+          reject(new Error(data.toString()))
+        })
+
+        child.on('close', async (data) => {
+          console.log('data=', data.toString())
+          this.logScheduler.ReturnLogger(successMessage(data.toString(), "使用localWhisper识别字幕完成"))
+          let textPath = path.join(outDir, '文案.txt')
+          if (!await CheckFileOrDirExist(textPath)) {
+            throw new Error('没有找到识别输出的文案文件')
+          }
+          let text = await fspromises.readFile(textPath, 'utf-8')
+          let textLines = text.split(/\r?\n/)
+          let lastLine = textLines[textLines.length - 1]
+          // 丢掉最后一行
+          textLines = textLines.slice(0, -1)
+
+          if (textLines.length != frameTimeList.length) {
+            throw new Error('分镜和识别文案数量不一致')
+          }
+          // 保存文案
+          for (let i = 0; i < textLines.length; i++) {
+            const element = textLines[i];
+            frameTimeList[i].text = element
+          }
+          // 写出
+          await fspromises.writeFile(path.join(global.config.project_path, '文案.txt'), textLines.join('\n'), 'utf-8')
+          if (data == 0) {
+            this.logScheduler.ReturnLogger(successMessage(null, "使用localWhisper识别字幕完成"))
+          } else {
+            this.logScheduler.ReturnLogger(errorMessage("使用localWhisper识别字幕失败，失败信息请查看日志"))
+          }
+          resolve();
+        })
+      })
+
+    } catch (error) {
+      this.logScheduler.ReturnLogger(errorMessage("使用localWhisper识别字幕失败，失败信息如下：" + error.message))
+      throw error
+    }
+  }
+  //#endregion
 }

src/main/Service/Subtitle/subtitleService.ts

@@ -11,7 +11,7 @@ import fs from 'fs'
 import { CheckFileOrDirExist } from "../../../define/Tools/file";
 import { BookServiceBasic } from "../ServiceBasic/bookServiceBasic";
 import { Subtitle } from "./subtitle";
-import { TaskScheduler } from "../task/taskScheduler";
+import { LogScheduler } from "../task/logScheduler";
 import { BookTaskStatus, BookType, OperateBookType } from "../../../define/enum/bookEnum";
 import { Book } from "../../../model/book";
 import { TimeStringToMilliseconds } from "../../../define/Tools/time";
@@ -20,7 +20,7 @@ export class SubtitleService {
   softWareServiceBasic: SoftWareServiceBasic
   bookServiceBasic: BookServiceBasic
   subtitle: Subtitle
-  taskScheduler: TaskScheduler
+  logScheduler: LogScheduler
   constructor() {
     this.softWareServiceBasic = new SoftWareServiceBasic();
     this.bookServiceBasic = new BookServiceBasic();

src/main/Service/ffmpegOptions.ts

@@ -98,8 +98,6 @@ export class FfmpegOptions {
 
   /**
    * FFmpeg裁剪视频，将一个视频将裁剪指定的时间内的片段
-   * @param {*} book 小说对象类
-   * @param {*} bookTask 小说批次任务对象类
    * @param {*} startTime 开始时间
    * @param {*} endTime 结束时间
    * @param {*} videoPath 视频地址
@@ -225,7 +223,7 @@ export class FfmpegOptions {
       // 判断分镜是不是和数据库中的数据匹配的上
       let res = await new Promise((resolve, reject) => {
         Ffmpeg(videoPath)
-          .inputOptions([`-ss ${MillisecondsToTimeString(frameTime)}`])
+          .inputOptions([`-ss ${MillisecondsToTimeString(Math.ceil(frameTime))}`])
           .output(outFramePath)
           .frames(1)
           .on('end', async function () {

src/main/Service/jianying/jianyingService.ts

@@ -0,0 +1,216 @@
+import path from 'path';
+import { CheckFileOrDirExist, DeleteFolderAllFile } from '../../../define/Tools/file';
+import fs from "fs";
+import { ValidateJson } from '../../../define/Tools/validate';
+import { FfmpegOptions } from '../ffmpegOptions';
+
+/**
+ * 存放剪映草稿的时间轴数据
+ */
+export type DraftTimeLineJson = {
+  name: string;
+  startTime: number;
+  endTime: number;
+  durationTime: number;
+  middleTime: number;
+  videoPath: string;
+  text: string;
+  framePath: string;
+  subVideoPath?: string;
+  audioPath?: string;
+}
+
+/**
+ * 剪映的一些服务
+ */
+class JianyingService {
+  draftTimeLine: DraftTimeLineJson[];
+  draftJson: any;
+  ffmpegOptions: FfmpegOptions
+  constructor() {
+    this.draftTimeLine = [];
+    this.ffmpegOptions = new FfmpegOptions();
+  }
+
+  /**
+   * 获取剪映草稿的关键帧和文本
+   * @param draftDir 草稿目录
+   * @param projectDir 项目目录
+   * @param packagePath 包路径
+   */
+  async GetDraftFrameAndText(draftDir: string, projectDir: string, packagePath: string) {
+    try {
+      // 获取草稿文件路径
+      let draftJsonPath = path.resolve(draftDir, "draft_content.json");
+      if (!await CheckFileOrDirExist(draftJsonPath)) {
+        throw new Error("剪映草稿文件不存在，请先检查");
+      }
+      // 读取草稿文件内容
+      let draftJsonString = await fs.promises.readFile(draftJsonPath, "utf-8");
+      if (!ValidateJson(draftJsonString)) {
+        throw new Error("剪映草稿文件格式错误，请检查");
+      }
+      this.draftJson = JSON.parse(draftJsonString);
+
+      // 检查输出文件夹是否存在
+      let projectTmp = path.resolve(projectDir, "tmp");
+      if (await CheckFileOrDirExist(projectTmp)) {
+        // 删除文件夹
+        await DeleteFolderAllFile(projectTmp);
+      }
+      // 创建输出文件夹
+      let projectInput = path.resolve(projectTmp, "input_crop");
+      console.log("projectInput", projectInput);
+
+      // 获取剪映的轨道，并且判断是否包含一个video轨道和一个text轨道
+      let draftTracks = this.draftJson.tracks;
+      if (!draftTracks) {
+        throw new Error("剪映草稿文件格式错误，没有轨道，请检查");
+      }
+      let hasVideo = draftTracks.some((track: any) => track.type === "video");
+      let hasText = draftTracks.some((track: any) => track.type === "text");
+
+      if (!(this.draftJson.tracks && hasVideo && hasText)) {
+        throw new Error("没有检测到剪映草稿文件中的video和text轨道，请检查");
+      }
+
+      // 获取视频节点
+      let videoNodes = draftTracks.filter((track: any) => track.type === "video")[0].segments;
+      this.GetVideoTime(videoNodes);
+
+      // 获取文本节点
+      let textNodes = draftTracks.filter((track: any) => track.type === "text")[0].segments;
+      this.GetTextTime(textNodes);
+
+      console.log("场景数：", this.draftTimeLine.length);
+
+      // 将数据写入到文件中
+      let txtData = this.draftTimeLine.map((item) => item.text);
+      let txtPath = path.resolve(projectDir, "文案.txt");
+      await fs.promises.writeFile(txtPath, txtData.join("\n"), "utf-8");
+
+      // 开始抽取关键帧
+      await this.GetDraftFrame(projectInput);
+
+      // 将数据写入到json文件中
+      let jsonPath = path.resolve(projectDir, "draftFrameData.json");
+      await fs.promises.writeFile(jsonPath, JSON.stringify(this.draftTimeLine), "utf-8");
+      console.log("GetDraftFrameAndText", jsonPath);
+    } catch (error) {
+      throw error;
+    }
+  }
+
+  /**
+   * 在节点数组中查找指定类型和值的节点
+   * @param nodes 节点数组
+   * @param type 节点类型
+   * @param value 节点值
+   * @returns 找到的节点
+   * @throws 如果没有找到对应的节点则抛出错误
+   */
+  private FindNode(nodes: any[], type: string, value: any) {
+    let res = nodes.filter((node: any) => node[type] === value);
+    if (res.length === 0) {
+      throw new Error("没有找到对应的节点");
+    }
+    return res[0];
+  }
+
+  /**
+   * 判断文本是否在时间轴内
+   * @param draftTimeObject 时间轴对象
+   * @param textStartTime 文本开始时间
+   * @param textEndTile 文本结束时间
+   * @returns 如果文本在时间轴内则返回 true，否则返回 false
+   */
+  private TextIsInTimeLine(draftTimeObject: DraftTimeLineJson, textStartTime: number, textEndTile: number) {
+    return textStartTime >= draftTimeObject.startTime && textEndTile <= draftTimeObject.endTime;
+  }
+
+  /**
+   * 抽取剪映草稿的关键帧
+   * @param projectInput 项目输入目录
+   */
+  private async GetDraftFrame(projectInput: string): Promise<void> {
+    for (let i = 0; i < this.draftTimeLine.length; i++) {
+      const element = this.draftTimeLine[i];
+      let outImagePath = path.resolve(projectInput, (i + 1).toString().padStart(5, "0") + ".png");
+
+      // 使用 ffmpeg 抽取关键帧
+      let frameRes = await this.ffmpegOptions.FfmpegGetFrame(element.middleTime / 1000, element.videoPath, outImagePath);
+      if (frameRes.code == 0) {
+        throw new Error(frameRes.message);
+      }
+      this.draftTimeLine[i].framePath = outImagePath;
+      console.log("已经抽取第", i + 1, "帧");
+    }
+  }
+
+  /**
+   * 获取文本时间
+   * @param textNodes 文本节点数组
+   */
+  private GetTextTime(textNodes: any[]): void {
+    let tempText = "";
+    let count = 0;
+    for (let i = 0; i < textNodes.length; i++) {
+      const element = textNodes[i];
+      let textStartTime = element.target_timerange.start;
+      let textEndTime = textStartTime + element.target_timerange.duration;
+      let textMaterialId = element.material_id;
+      let textMaterialNode = this.FindNode(this.draftJson.materials.texts, "id", textMaterialId);
+      let textContent = textMaterialNode.content;
+      let textContentJson = JSON.parse(textContent);
+
+      let text = textContentJson.text + "。";
+
+      // 不在视频的时间轴内，丢弃
+      if (count > this.draftTimeLine.length - 1) {
+        break;
+      }
+      if (this.TextIsInTimeLine(this.draftTimeLine[count], textStartTime, textEndTime)) {
+        tempText += text;
+        if (i == textNodes.length - 1) {
+          this.draftTimeLine[count].text = tempText;
+        }
+      } else {
+        this.draftTimeLine[count].text = tempText;
+        tempText = text;
+        count += 1;
+      }
+    }
+  }
+
+  /**
+   * 获取视频时间
+   * @param videoNodes 视频节点数组
+   */
+  private GetVideoTime(videoNodes: any[]): void {
+    for (let i = 0; i < videoNodes.length; i++) {
+      const element = videoNodes[i];
+      let startTime = element.target_timerange.start;
+      let endTime = startTime + element.target_timerange.duration;
+      let durationTime = element.target_timerange.duration;
+      let middleTime = startTime + ((endTime - startTime) / 2);
+
+      let videoId = element.material_id;
+      let materialNode = this.FindNode(this.draftJson.materials.videos, "id", videoId);
+      let videoPath = materialNode.path;
+      this.draftTimeLine.push({
+        name: (i + 1).toString().padStart(5, "0"),
+        startTime,
+        endTime,
+        durationTime,
+        middleTime,
+        videoPath,
+        text: "",
+        framePath: undefined
+      })
+    }
+  }
+
+}
+
+
+export default JianyingService;

src/main/Service/task/logScheduler.ts

@@ -4,7 +4,7 @@ import { LoggerStatus, OtherData } from '../../../define/enum/softwareEnum'
 import { successMessage, errorMessage } from '../../Public/generalTools'
 import { GeneralResponse } from '../../../model/generalResponse'
 
-export class TaskScheduler {
+export class LogScheduler {
   constructor() { }
   /**
    * 添加日志到数据库，然后返回日志信息到前端，日志记录失败不会报错
@@ -20,7 +20,7 @@ export class TaskScheduler {
     type: string,
     content: string,
     bookTaskId: string,
-    status = LoggerStatus.DOING
+    status: LoggerStatus = LoggerStatus.DOING
   ): Promise<GeneralResponse.ErrorItem | GeneralResponse.SuccessItem> {
     try {
       let log = {
@@ -38,7 +38,16 @@ export class TaskScheduler {
 
       return res
     } catch (error) {
-      return errorMessage(error.message, 'TaskScheduler_AddLogToDB')
+      return errorMessage(error.message, 'LogScheduler_AddLogToDB')
     }
   }
+
+  /**
+   * 将日志返回到前端
+   * @param {*} log 日志信息
+   * @returns
+   */
+  ReturnLogger(log: GeneralResponse.ErrorItem | GeneralResponse.SuccessItem) {
+    global.newWindow[0].win.webContents.send(DEFINE_STRING.SYSTEM.RETURN_LOGGER, log)
+  }
 }

src/main/Service/videoService/videoHandle.ts

@@ -0,0 +1,333 @@
+
+import path from 'path';
+import { CheckFileOrDirExist, DeleteFolderAllFile } from '../../../define/Tools/file';
+import fs from 'fs';
+import { LogScheduler } from '../task/logScheduler';
+import { successMessage } from '../../Public/generalTools';
+import { define } from '../../../define/define';
+import util from 'util';
+import { exec } from 'child_process';
+import { ValidateJson } from '../../../define/Tools/validate';
+import { DraftTimeLineJson } from '../jianying/jianyingService';
+const execAsync = util.promisify(exec)
+import { FfmpegOptions } from '../ffmpegOptions';
+import { TimeStringToMilliseconds } from '../../../define/Tools/time';
+import { isEmpty } from 'lodash';
+import { Subtitle } from '../Subtitle/subtitle';
+
+
+type VideoHandleShortVideoTimeLine = {
+  name: string,
+  startTime: number;
+  endTime: number;
+  videoPath: string,
+  duration: number
+}
+
+class VideoHandle {
+  logScheduler: LogScheduler;
+  ffmpegOptions: FfmpegOptions;
+  subtitle: Subtitle;
+  constructor() {
+    this.logScheduler = new LogScheduler()
+    this.ffmpegOptions = new FfmpegOptions();
+    this.subtitle = new Subtitle();
+  }
+
+
+  public async StartStoryboarding(videoPath: string, sensitivity: number) {
+    // 检查抽帧文件是不是存在
+    let framePath = path.resolve(global.config.project_path, "data/frame");
+    if (await CheckFileOrDirExist(framePath)) {
+      await DeleteFolderAllFile(framePath);
+    } else {
+      await fs.promises.mkdir(framePath, { recursive: true })
+    }
+    // 检查输入文件是不是存在
+    let inputPath = path.resolve(global.config.project_path, "tmp/input_crop");
+    if (await CheckFileOrDirExist(inputPath)) {
+      await DeleteFolderAllFile(inputPath);
+    } else {
+      await fs.promises.mkdir(inputPath, { recursive: true })
+    }
+
+    // 检查本事localwhisper是不是存在
+    let localwhisperPath = path.resolve(define.scripts_path, "localWhisper/local_whisper.exe");
+    if (!await CheckFileOrDirExist(localwhisperPath)) {
+      throw new Error('localwhisper 不存在，请查看文档安装localwhisper插件环境');
+    }
+
+    // 判断输出文件是不是存在，存在删除
+    let frameJson = path.resolve(global.config.project_path, "data/frameTimeLine.json");
+    if (await CheckFileOrDirExist(frameJson)) {
+      await fs.promises.unlink(frameJson);
+    }
+
+    // 开始计算分镜
+    let frameTimeList = await this.ComputedFrameTime(videoPath, frameJson, sensitivity);
+
+    // 开始对视频进行切割
+    // 先计算时间点
+    let shortVideo = [] as VideoHandleShortVideoTimeLine[];
+    shortVideo = await this.VideoShortClip(frameTimeList, videoPath, 0.5 * 60 * 1000);
+
+    // 检查长度
+    if (shortVideo.length != frameTimeList.length) {
+      throw new Error('分镜数据和切割视频数据不一致，请检查');
+    }
+
+    // 开始切割视频
+    console.log(shortVideo);
+    let subVideoPath = await this.CutViodeToShortClip(shortVideo, frameTimeList) as string[];
+
+    // 开始抽帧
+    await this.GetFrameFromCutVideo(shortVideo, inputPath, subVideoPath, frameTimeList);
+
+    // 开始分离音频
+    await this.SplitAudio(frameTimeList, framePath);
+
+    // 开始提取字幕
+    await this.subtitle.GetTextByLocalWhisper(frameTimeList, framePath, framePath, localwhisperPath);
+
+    console.log(frameTimeList);
+    await fs.promises.writeFile(frameJson, JSON.stringify(frameTimeList), 'utf-8');
+  }
+
+  /**
+   * 分离音频
+   * @param frameTimeList 
+   * @param framePath 
+   */
+  async SplitAudio(frameTimeList: DraftTimeLineJson[], framePath: string) {
+    for (let i = 0; i < frameTimeList.length; i++) {
+      const element = frameTimeList[i];
+      if (isEmpty(element.subVideoPath)) {
+        throw new Error('没有找到待分离的视频数据，请检查');
+      }
+      if (!await CheckFileOrDirExist(element.subVideoPath)) {
+        throw new Error(`视频片段 ${element.subVideoPath} 不存在，请检查`);
+      }
+      let audioPath = path.resolve(framePath, `${element.name}.mp3`);
+      if (await CheckFileOrDirExist(audioPath)) {
+        await fs.promises.unlink(audioPath);
+      }
+      let res = await this.ffmpegOptions.FfmpegExtractAudio(element.subVideoPath, audioPath)
+      if (res.code == 0) {
+        throw new Error(res.message);
+      }
+      if (!await CheckFileOrDirExist(audioPath)) {
+        throw new Error(`分离音频 ${audioPath} 失败，没有找到分离后的音频文件，请检查`);
+      }
+      element.audioPath = audioPath;
+    }
+  }
+
+
+  async GetFrameFromCutVideo(shortVideo: VideoHandleShortVideoTimeLine[], inputPath: string, subVideoPath: string[], frameTimeList: DraftTimeLineJson[]) {
+    if (shortVideo.length != subVideoPath.length) {
+      throw new Error('视频片段和分镜数据不一致');
+    }
+    if (shortVideo.length != frameTimeList.length) {
+      throw new Error('视频片段和分镜数据不一致');
+    }
+
+    let imagePath = [] as string[];
+    for (let i = 0; i < shortVideo.length; i++) {
+      const element = shortVideo[i];
+      if (!frameTimeList[i]) {
+        throw new Error('分镜数据和切割视频数据不一致，请检查');
+      }
+
+      let middleTime = element.startTime + ((element.endTime - element.startTime) / 2);
+      let outImagePath = path.resolve(inputPath, `${element.name}.png`);
+      let res = await this.ffmpegOptions.FfmpegGetFrame(middleTime, element.videoPath, outImagePath);
+      if (res.code == 0) {
+        throw new Error(res.message);
+      }
+      imagePath.push(outImagePath);
+      // 检查图片是否存在
+      if (!await CheckFileOrDirExist(outImagePath)) {
+        throw new Error(`抽取的图片 ${outImagePath} 不存在，请检查`);
+      }
+      frameTimeList[i].framePath = outImagePath;
+    }
+    return imagePath;
+  }
+
+  /**
+   * 将长视频按照指定的视频长度，给分割为一个个的小视频片段
+   * @param shortVideo 
+   */
+  async CutViodeToShortClip(shortVideo: VideoHandleShortVideoTimeLine[], frameTimeList: DraftTimeLineJson[]): Promise<string[]> {
+    let subVideoPaths = [] as string[];
+    for (let i = 0; i < shortVideo.length; i++) {
+      const element = shortVideo[i];
+      if (!frameTimeList[i]) {
+        throw new Error('分镜数据和切割视频数据不一致，请检查');
+      }
+      let subVideoPath = path.resolve(global.config.project_path, `data/frame/${element.name}.mp4`);
+      // 开始截取视频
+      let res = await this.ffmpegOptions.FfmpegCutVideo(
+        element.startTime,
+        element.endTime,
+        element.videoPath,
+        subVideoPath
+      )
+      subVideoPaths.push(subVideoPath);
+
+      if (res.code == 0) {
+        throw new Error(res.message);
+      }
+      if (!await CheckFileOrDirExist(subVideoPath)) {
+        throw new Error(`截取视频片段 ${subVideoPath} 不存在，请检查`);
+      }
+      frameTimeList[i].subVideoPath = subVideoPath;
+    }
+    return subVideoPaths;
+  }
+
+  /**
+   * 预处理视频，将视频切割成小段，减少计算时间
+   * @param frameTimeList 要处理的时间线，是个json数组
+   * @param videoPath 要处理的视频地址
+   * @param duration 视频的持续时间
+   * @returns 
+   */
+  public async VideoShortClip(frameTimeList: any[], videoPath: string, duration: number): Promise<VideoHandleShortVideoTimeLine[]> {
+    let shortVideo = [] as VideoHandleShortVideoTimeLine[];
+    let durationTime = 0; // 小视频片段的持续时间
+    // let duration = 5 * 60 * 1000; // 5分钟
+    let tempCount = 0;
+    let shotVideoPath = path.resolve(global.config.project_path, `data/temp_frame_${tempCount}.mp4`); // 新的视频路径
+    let startTime = 0; // 开始时间
+    let endTime = 0; // 结束时间
+    let lastEndTime = 0; // 上一个结束时间  
+    for (let i = 0; i < frameTimeList.length; i++) {
+      const item = frameTimeList[i];
+      let temRes = {
+        name: (i + 1).toString().padStart(5, "0"),
+        startTime: item.startTime - lastEndTime,
+        endTime: item.endTime - lastEndTime,
+        videoPath: shotVideoPath,
+        duration: item.endTime - item.startTime
+      }
+      endTime = item.endTime;
+      durationTime += item.endTime - item.startTime;
+      if (durationTime > duration) { // 判断条件切割视频
+        // 开始切割视频
+        let res = await this.ffmpegOptions.FfmpegCutVideo(
+          startTime,
+          endTime,
+          videoPath,
+          shotVideoPath
+        )
+        if (res.code == 0) {
+          throw new Error(res.message);
+        }
+        lastEndTime = item.endTime;
+        tempCount++;
+        durationTime = 0;
+        startTime = endTime;
+        endTime = 0;
+        shotVideoPath = path.resolve(global.config.project_path, `data/temp_frame_${tempCount}.mp4`);
+      }
+      shortVideo.push(temRes)
+    }
+    // 最后一个也要切割
+    if (durationTime > 0) {
+      let res = await this.ffmpegOptions.FfmpegCutVideo(
+        startTime,
+        endTime,
+        videoPath,
+        shotVideoPath
+      )
+      if (res.code == 0) {
+        throw new Error(res.message);
+      }
+    }
+    // 将数据写出
+    let shortVideoJson = path.resolve(global.config.project_path, "data/shortVideo.json");
+    await fs.promises.writeFile(shortVideoJson, JSON.stringify(shortVideo), 'utf-8');
+    return shortVideo;
+  }
+
+
+  /**
+   * 计算视频的帧时间。
+   *
+   * @param {string} videoPath - 视频文件的路径。
+   * @param {number} sensitivity - 分镜的敏感度。
+   * @throws {Error} 如果视频文件不存在或分镜失败，将抛出错误。
+   *
+   * @remarks
+   * 该方法首先检查视频文件是否存在，如果不存在则抛出错误。
+   * 然后检查输出文件是否存在，如果存在则删除。
+   * 接着调用外部程序进行分镜处理，并记录日志。
+   * 如果分镜成功但有警告信息，将记录警告日志。
+   * 最后检查分镜输出文件是否存在并读取数据，如果没有找到输出文件或数据为空，将抛出错误。
+   */
+  public async ComputedFrameTime(videoPath: string, frameJson: string, sensitivity: number): Promise<DraftTimeLineJson[]> {
+
+    if (!await CheckFileOrDirExist(videoPath)) {
+      throw new Error('视频文件不存在，请检查');
+    }
+
+    this.logScheduler.ReturnLogger(successMessage(null, "前置检查结束，开始进行分镜", "VideoHandle_StartStoryboarding"));
+
+    // 开始调用分镜
+    let command = `"${path.join(
+      define.scripts_path,
+      'Lai.exe'
+    )}" "-ka" "${videoPath}" "${frameJson}" "${sensitivity}"`
+    const output = await execAsync(command, {
+      maxBuffer: 1024 * 1024 * 10,
+      encoding: 'utf-8'
+    })
+    // 有错误输出
+    if (output.stderr != '') {
+      let error_msg = `分镜成功，但有警告提示：${output.stderr}`
+      this.logScheduler.ReturnLogger(successMessage(null, error_msg, "VideoHandle_StartStoryboarding"));
+    }
+
+    // 分镜成功，处理输出
+    let josnIsExist = await CheckFileOrDirExist(frameJson);
+    if (!josnIsExist) {
+      let error_message = `分镜失败，没有找到对应的分镜输出文件：${frameJson}`
+      this.logScheduler.ReturnLogger(successMessage(null, error_message, "VideoHandle_StartStoryboarding"));
+      throw new Error(error_message);
+    }
+    let frameJsonDataString = await fs.promises.readFile(frameJson, 'utf-8');
+    let res = ValidateJson(frameJsonDataString);
+    if (!res) {
+      throw new Error('分镜数据不是有效的JSON格式，请检查');
+    }
+    let frameJsonData = JSON.parse(frameJsonDataString);
+    if (frameJsonData.length <= 0) {
+      let error_msg = `分镜失败，没有找到对应的分镜数据`
+      this.logScheduler.ReturnLogger(successMessage(null, error_msg, "VideoHandle_StartStoryboarding"));
+      throw new Error(error_msg);
+    }
+    let result = [] as DraftTimeLineJson[];
+    // 这边将分镜的数据进行一个处理
+    for (let i = 0; i < frameJsonData.length; i++) {
+      const element = frameJsonData[i];
+      let st = TimeStringToMilliseconds(element[0]);
+      let et = TimeStringToMilliseconds(element[1]);
+      let tempObject = {
+        name: (i + 1).toString().padStart(5, "0"),
+        startTime: st,
+        endTime: et,
+        middleTime: st + ((et - st) / 2),
+        videoPath: videoPath,
+        framePath: '',
+        text: "",
+        durationTime: et - st
+      } as DraftTimeLineJson;
+      result.push(tempObject);
+    }
+    return result;
+  }
+
+}
+
+export default VideoHandle;

src/main/Service/watermark.ts

@@ -13,7 +13,7 @@ import { define } from '../../define/define'
 import { LOGGER_DEFINE } from '../../define/logger_define'
 import axios from 'axios'
 import { Base64ToFile, GetImageBase64 } from '../../define/Tools/image'
-import { TaskScheduler } from './task/taskScheduler';
+import { LogScheduler } from './task/logScheduler';
 import { LoggerStatus, OtherData, ResponseMessageType } from '../../define/enum/softwareEnum';
 import { basicApi } from '../../api/apiBasic';
 import { FfmpegOptions } from './ffmpegOptions';
@@ -28,7 +28,7 @@ import { BookTaskService } from '../../define/db/service/Book/bookTaskService';
 
 export class Watermark {
   softwareService: SoftwareService
-  taskScheduler: TaskScheduler;
+  logScheduler: LogScheduler;
   bookService: BookService
   bookTaskDetailService: BookTaskDetailService
   bookTaskService: BookTaskService
@@ -39,8 +39,8 @@ export class Watermark {
     if (!this.softwareService) {
       this.softwareService = await SoftwareService.getInstance()
     }
-    if (!this.taskScheduler) {
+    if (!this.logScheduler) {
-      this.taskScheduler = new TaskScheduler()
+      this.logScheduler = new LogScheduler()
     }
     if (!this.bookService) {
       this.bookService = await BookService.getInstance()
@@ -449,7 +449,7 @@ export class Watermark {
         }, DEFINE_STRING.BOOK.REMOVE_WATERMARK_RETURN)
 
 
-        this.taskScheduler.AddLogToDB(book.id, book.type, `${element.name} 去除水印完成`, element.bookTaskId, LoggerStatus.SUCCESS)
+        this.logScheduler.AddLogToDB(book.id, book.type, `${element.name} 去除水印完成`, element.bookTaskId, LoggerStatus.SUCCESS)
       }
       // 全部完毕
       if (operateBookType == OperateBookType.BOOKTASKDETAIL) {

src/preload/index.js

@@ -73,9 +73,8 @@ const api = {
   },
 
   // 分镜语音识别消息
-  StartStoryboarding: async (value) => {
+  StartStoryboarding: async (value) =>
-    let res = await ipcRenderer.invoke(DEFINE_STRING.START_STORY_BOARDING, value)
+    await ipcRenderer.invoke(DEFINE_STRING.START_STORY_BOARDING, value),
-  },
 
   // 获取设置的初始数据
   getSettingDafultData: async (callback) =>

src/renderer/src/components/Backstep/GetFrame.vue

@@ -37,7 +37,6 @@
         label-placement="left"
         inline
         :model="frameValue"
-        :rules="rules"
         size="medium"
       >
         <n-form-item label="分割敏感度" path="sensitivity" style="width: 300px">
@@ -68,7 +67,7 @@
   <n-code style="padding: 0; font-size: small" :code="code" language="js" word-wrap />
 </template>
 
-<script>
+<script setup>
 import { defineComponent, ref, onMounted, toRaw } from 'vue'
 import {
   NSelect,
@@ -83,39 +82,26 @@ import {
   NForm,
   NFormItem,
   NSlider,
-  NInput
+  NInput,
+  useDialog
 } from 'naive-ui'
 import { DEFINE_STRING } from '../../../../define/define_string'
-export default defineComponent({
-  components: {
-    NSelect,
-    NButton,
-    NSpin,
-    NDivider,
-    NCode,
-    NTabs,
-    NTabPane,
-    NSpace,
-    NForm,
-    NFormItem,
-    NSlider,
-    NInput
-  },
-  setup() {
-    let options = []
-    let out_dir = ref(null)
-    let selectedValue = ref(null)
-    let show = ref(false)
-    let code = ref('')
-    const message = useMessage()
-    let storyLoading = ref(false)
 
-    let frameValue = ref({
+let options = []
+let out_dir = ref(null)
+let selectedValue = ref(null)
+let show = ref(false)
+let code = ref('')
+const message = useMessage()
+let storyLoading = ref(false)
+let dialog = useDialog()
+
+let frameValue = ref({
   sensitivity: 30,
   video_path: null
-    })
+})
 
-    onMounted(() => {
+onMounted(() => {
   window.api.getDraftFileList((value) => {
     value.forEach((element) => {
       let obj = {
@@ -138,9 +124,9 @@ export default defineComponent({
     }
     code.value = code.value + '\n' + value.data
   })
-    })
+})
 
-    async function getFrameFunc(e) {
+async function getFrameFunc(e) {
   out_dir = window.config.project_path
   if (selectedValue.value == null || selectedValue.value == undefined) {
     message.error('请选择剪映草稿和输出草稿')
@@ -158,9 +144,9 @@ export default defineComponent({
     code.value = value.data
     show.value = false
   })
-    }
+}
 
-    function selectExportFolder(e) {
+function selectExportFolder(e) {
   window.api.selectFolder(null, (value) => {
     if (value.length <= 0) {
       message.error('必须选择输出文件夹位置')
@@ -168,12 +154,12 @@ export default defineComponent({
     }
     out_dir.value = value[0]
   })
-    }
+}
 
-    /**
+/**
  * 选择指定的视频文件
  */
-    async function GetVideoFile() {
+async function GetVideoFile() {
   await window.api.SelectFile(['mp4'], (value) => {
     if (value.code == 0) {
       message.error(value.message)
@@ -181,12 +167,12 @@ export default defineComponent({
     }
     frameValue.value.video_path = value.value
   })
-    }
+}
 
-    /**
+/**
  * 开始分镜执行分镜任务
  */
-    async function StartStoryboarding() {
+async function StartStoryboarding() {
   storyLoading.value = true
   if (frameValue.value.video_path == null) {
     message.error('选择分镜的视频地址')
@@ -202,42 +188,36 @@ export default defineComponent({
     return
   }
 
-      await window.api.StartStoryboarding(toRaw(frameValue.value))
+  let res = await window.api.StartStoryboarding(toRaw(frameValue.value))
+  if (res.code == 0) {
+    dialog.error({
+      title: '抽帧错误输出',
+      content: res.message
+    })
+    return
+  } else {
+    dialog.success({
+      title: '抽帧成功',
+      content: '视频分镜，抽帧，问题提取都已完成'
+    })
   }
+}
 
-    /**
+/**
  * 打开环境安装网站
  */
-    function OpenTeachDoc() {
+function OpenTeachDoc() {
   window.api.OpenUrl(
     'https://pvwu1oahp5m.feishu.cn/docx/VrBVd2KUDosmNfxat3OceWuInjd?from=from_copylink'
   )
-    }
+}
 
-    function openExportFolder() {
+function openExportFolder() {
   window.system.OpenFolder({
     folderPath: 'tmp/input_crop',
     baseProject: true
   })
-    }
+}
-
-    return {
-      selectedValue,
-      options,
-      out_dir,
-      getFrameFunc,
-      selectExportFolder,
-      show,
-      code,
-      frameValue,
-      GetVideoFile,
-      StartStoryboarding,
-      OpenTeachDoc,
-      storyLoading,
-      openExportFolder
-    }
-  }
-})
 </script>
 
 <style>

src/renderer/src/components/Book/Components/ManageBook/ManageBookShowLogger.vue

@@ -47,7 +47,6 @@ export default defineComponent({
     onMounted(async () => {
       // 监听返回的日志数据
       window.api.setEventListen([DEFINE_STRING.SYSTEM.RETURN_LOGGER], (value) => {
-        debuger
         if (value.code == 0) {
           message.error('添加日志输出失败，但是不影响使用')
           logger.value += value.message + '\n'

src/renderer/src/components/Home/ShowMessage.vue

@@ -1,9 +1,8 @@
 <template>
   <div style="width: 100%; height: 100%">
-    <div
+    <div style="font-size: 15px; display: flex; justify-content: center; width: 100%; height: 100%">
-      id="showmessage"
+      <div id="showmessage"></div>
-      style="font-size: 15px; display: flex; justify-content: center; width: 100%; height: 100%"
+    </div>
-    ></div>
   </div>
 </template>
 
@@ -34,6 +33,7 @@ async function GetRemoteSystemInformation() {
       iframe.style.padding = '0'
       iframe.style.height = '98vh' // Adjust the height as needed
       showMessageDiv.innerHTML = ''
+      showMessageDiv.style.width = '100%'
       showMessageDiv.appendChild(iframe)
     } else {
       showMessageDiv.innerHTML = remoteHomePage