upd done

conf.ini

+云扬，男，年轻人
+2.50(10字/秒)
\ No newline at end of file

detect_dialog.py

@@ -5,8 +5,7 @@ from PyQt5.QtGui import *;
 from PyQt5.QtWidgets import *;
 
 from detect_dialog_ui import Ui_Dialog
-from utils import validate_and_get_filepath
-
+from utils import validate_and_get_filepath, replace_path_suffix
 
 
 class Detect_Dialog(QDialog, Ui_Dialog):
@@ -22,10 +21,11 @@ class Detect_Dialog(QDialog, Ui_Dialog):
         self.pushButton_2.clicked.connect(self.openTableFile)
         self.buttonBox.button(QDialogButtonBox.StandardButton.Ok).clicked.connect(self.start_detect)
     def openFile(self):
-        file_info = QFileDialog.getOpenFileNames(self, '选择视频', os.getcwd(), "All Files(*);;Text Files(*.txt)")
+        file_info = QFileDialog.getOpenFileNames(self, '选择视频', os.getcwd(), "MP4(*.mp4);;Text Files(*.txt)")
         file_name, ok = validate_and_get_filepath(file_info)
         if ok:
             self.lineEdit.setText(file_name)
+            self.lineEdit_2.setText(replace_path_suffix(file_info[0][0], ".xlsx"))
     def openTableFile(self):
         now_path = os.path.join(os.getcwd(), self.lineEdit.text())
         now_path = now_path.replace(os.path.splitext(now_path)[-1], ".xlsx")

detect_with_ocr.py

@@ -27,7 +27,7 @@ import re
 from typing import Tuple, Union
 
 from detect_with_asr import create_sheet, write_to_sheet
-
+from main_window import MainWindow, Element
 # 字幕的上下边界
 up_b, down_b = 0, 0
 
@@ -186,8 +186,7 @@ def detect_subtitle(img: np.ndarray) -> Union[str, None]:
     subTitle = ''
     height = down_b - up_b
     img = img[int(up_b - height * 0.7):int(down_b + height * 0.7)]
-    # todo：这里怎么做
-    img = cv2.resize(img, (int(img.shape[1] * 0.5), int(img.shape[0] * 0.5)))
+    # img = cv2.resize(img, (int(img.shape[1] * 0.5), int(img.shape[0] * 0.5)))
     res = ocr.ocr(img, cls=True)
     sorted(res, key=lambda text: text[0][0][1])
     if len(res) == 0:
@@ -217,7 +216,7 @@ def detect_subtitle(img: np.ndarray) -> Union[str, None]:
     return None
 
 
-def process_video(video_path: str, begin: float, end: float, book_path: str, sheet_name: str, state=None):
+def process_video(video_path: str, begin: float, end: float, book_path: str, sheet_name: str, state=None, mainWindow: MainWindow=None):
     """处理视频，主要完成对字幕的捕捉以及根据字幕分析得出旁白可能位置的任务
 
     Args:
@@ -249,10 +248,13 @@ def process_video(video_path: str, begin: float, end: float, book_path: str, she
             if video.get(cv2.CAP_PROP_POS_MSEC) / 1000 - end_time > 1:
                 print('--------------------------------------------------')
                 recommend_lens = int((video.get(cv2.CAP_PROP_POS_MSEC) / 1000 - end_time) * normal_speed)
-                write_to_sheet(book_path, sheet_name, ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+                # write_to_sheet(book_path, sheet_name, ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+                add_to_list(mainWindow, "旁白", ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+
                 # 判断当前是否有字幕需要被保存下来
             if end_time < start_time:
-                write_to_sheet(book_path, sheet_name, [round(start_time, 2), round(end, 2), lastSubTitle, ''])
+                # write_to_sheet(book_path, sheet_name, [round(start_time, 2), round(end, 2), lastSubTitle, ''])
+                add_to_list(mainWindow, "字幕", [round(start_time, 2), round(end, 2), lastSubTitle, ''])
             break
         # 每秒取4帧画面左右
         if cnt % int(fps / 4) == 0:
@@ -272,12 +274,13 @@ def process_video(video_path: str, begin: float, end: float, book_path: str, she
                     print('--------------------------------------------------')
                     recommend_lens = int(res[-1][0] * normal_speed) if len(res) == 1 else int(
                         (res[-1][0] - res[-2][1]) * normal_speed)
-                    # narratage_recommend.append(['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
-                    write_to_sheet(book_path, sheet_name, ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+                    # write_to_sheet(book_path, sheet_name, ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+                    add_to_list(mainWindow, "旁白", ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
                 print(start_time, end_time, lastSubTitle)
-                # narratage_recommend.append([round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
-                write_to_sheet(book_path, sheet_name, [round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
-            # 两句话连在一起，但是两句话不一样
+
+                # write_to_sheet(book_path, sheet_name, [round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
+                add_to_list(mainWindow,"字幕", [round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
+                # 两句话连在一起，但是两句话不一样
             elif lastSubTitle is not None and subTitle is not None:
                 if string_similar(lastSubTitle, subTitle) < 0.7:
                     end_time = video.get(cv2.CAP_PROP_POS_MSEC) / 1000
@@ -286,11 +289,11 @@ def process_video(video_path: str, begin: float, end: float, book_path: str, she
                         print('--------------------------------------------------')
                         recommend_lens = int(res[-1][0] * normal_speed) if len(res) == 1 else int(
                             (res[-1][0] - res[-2][1]) * normal_speed)
-                        # narratage_recommend.append(['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
-                        write_to_sheet(book_path, sheet_name, ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+                        # write_to_sheet(book_path, sheet_name, ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
+                        add_to_list(mainWindow, "旁白", ['', '', '', '插入旁白，推荐字数为%d' % recommend_lens])
                     print(start_time, end_time, lastSubTitle)
-                    # narratage_recommend.append([round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
-                    write_to_sheet(book_path, sheet_name, [round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
+                    # write_to_sheet(book_path, sheet_name, [round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
+                    add_to_list(mainWindow, "字幕", [round(start_time, 2), round(end_time, 2), lastSubTitle, ''])
                     start_time = end_time
                 else:
                     lastSubTitle = subTitle if len(subTitle) > len(lastSubTitle) else lastSubTitle
@@ -298,8 +301,29 @@ def process_video(video_path: str, begin: float, end: float, book_path: str, she
             # 当前字幕与上一段字幕不一样
             lastSubTitle = subTitle
 
+def add_to_list(mainWindow: MainWindow, element_type: str, li: list):
+
+    st_time_sec, ed_time_sec, subtitle, suggest = li
+    st_time_sec, ed_time_sec = str(st_time_sec), str(ed_time_sec)
+    aside = ""
+    i = len(mainWindow.projectContext.all_elements)
+    if element_type == "字幕":
+        mainWindow.projectContext.subtitle_list.append(Element(st_time_sec, ed_time_sec, subtitle, suggest, aside))
+        mainWindow.projectContext.all_elements.append(mainWindow.projectContext.subtitle_list[-1])
+    else:
+        if i == 0:
+            st_time_sec = "0.01"
+        else:
+            st_time_sec = "%.2f" % (float(mainWindow.projectContext.all_elements[i - 1].ed_time_sec) + 0.01)
+
+        # 因为暂时没有用到ed_time_sec，所以直接赋值空吧
+        ed_time_sec = ""
+
+        mainWindow.projectContext.aside_list.append(Element(st_time_sec, ed_time_sec, subtitle, suggest, aside))
+        mainWindow.projectContext.all_elements.append(mainWindow.projectContext.aside_list[-1])
+
 
-def detect_with_ocr(video_path: str, book_path: str, start_time: float, end_time: float, state=None):
+def detect_with_ocr(video_path: str, book_path: str, start_time: float, end_time: float, state=None, mainWindow: MainWindow=None):
     """使用ocr检测视频获取字幕并输出旁白推荐
 
     Args:
@@ -321,14 +345,14 @@ def detect_with_ocr(video_path: str, book_path: str, start_time: float, end_time
     global up_b, down_b
     # print("get the bounding of the narratage at time: ", datetime.datetime.now())
     # 此处start_time + 300是为了节省用户调整视频开始时间的功夫（强行跳过前5分钟）
-    up_b, down_b = get_position(video_path, start_time+300)
+    up_b, down_b = get_position(video_path, start_time)
 
     # 获取并构建输出信息
     table_head = [["起始时间", "终止时间", "字幕", '建议', '解说脚本']]
     # print("create sheet at time: ", datetime.datetime.now())
     create_sheet(book_name_xlsx, sheet_name_xlsx, table_head)
     # print("process the total video at time: ", datetime.datetime.now())
-    process_video(video_path, start_time, end_time, book_name_xlsx, sheet_name_xlsx, state)
+    process_video(video_path, start_time, end_time, book_name_xlsx, sheet_name_xlsx, state, mainWindow)
 
 
 if __name__ == '__main__':

main_window.py

@@ -11,6 +11,7 @@ from detect_dialog import Detect_Dialog
 from assemble_dialog import Assemble_Dialog
 from prompt_dialog import Prompt_Dialog
 from setting_dialog import Setting_Dialog
+from operation_dialog import Operation_Dialog
 from synthesis import SynthesisProcessor
 from myVideoWidget import myVideoWidget
 from myvideoslider import myVideoSlider
@@ -45,6 +46,12 @@ class MainWindow(QMainWindow, Ui_MainWindow):
         #提示框
         self.prompt_dialog = Prompt_Dialog()
 
+        #操作框
+        self.operation_dialog = Operation_Dialog(self)
+        self.operation_dialog.start_add_signal.connect(self.add_line_operation_slot)
+        self.operation_dialog.start_del_signal.connect(self.del_line_operation_slot)
+
+
         #所有QTimer集中管理
         self.detect_timer = QTimer()
         self.detect_timer.timeout.connect(self.check_if_detect_over_slot)
@@ -87,10 +94,13 @@ class MainWindow(QMainWindow, Ui_MainWindow):
         self.action_save.triggered.connect(self.save_project)
         self.import_movie.triggered.connect(self.import_slot)
         self.action_open_project.triggered.connect(self.open_project_slot)
+        self.action_refresh_tab.triggered.connect(self.refresh_tab_slot)
 
         self.action_undo.triggered.connect(self.undo_slot)
         self.action_redo.triggered.connect(self.redo_slot)
         self.action_view_history.triggered.connect(self.view_history_slot)
+        self.action_operate.triggered.connect(self.operate_slot)
+
 
         # 状态栏的动作
         # self.statusbar.addPermanentWidget(self.statusbarButton, stretch=0)
@@ -212,6 +222,8 @@ class MainWindow(QMainWindow, Ui_MainWindow):
         #     self.show_warning_msg_box("请确认结束时间是否正确")
         #     return
 
+        self.projectContext.Init(os.path.dirname(book_path), os.path.basename(book_path))
+
         # 获取视频的时长等信息，初始化开始结束时间
         startTime = "00:00:00"
 
@@ -248,10 +260,10 @@ class MainWindow(QMainWindow, Ui_MainWindow):
         # threads.append(t)
 
         from narratage_detection import detect
-        # todo:先只支持有字幕的
+
         t = RunThread(funcName=detect,
                       args=(video_path, start_time, end_time,
-                            book_path, state, 1),
+                            book_path, state, 1,self),
                       name="detect")
         t.setDaemon(True)
         self.threads.append(t)
@@ -384,6 +396,7 @@ class MainWindow(QMainWindow, Ui_MainWindow):
                           args=(audio_path, self.previewed_audio),
                           name="play_audio").start()
 
+
     @staticmethod
     #一条语音的最长播放时间是10秒
     def play_audio(path, previewed_audio):
@@ -515,7 +528,7 @@ class MainWindow(QMainWindow, Ui_MainWindow):
         return False
 
     def save_project(self):
-        err_info = self.projectContext.save_project()
+        err_info = self.projectContext.save_project(True)
         if err_info == None:
             self.prompt_dialog.show_dialog_signal.emit("保存工程成功")
         else:
@@ -572,7 +585,10 @@ class MainWindow(QMainWindow, Ui_MainWindow):
     def rewriteHistory(self, item):
         if self.projectContext.initial_ing == True:
             return
+
+        # 合成这一段语音
         from speech_synthesis import speech_synthesis, Speaker, choose_speaker
+        print("self.projectContext.excel_path:", self.projectContext.excel_path)
         audio_dir = os.path.dirname(self.projectContext.excel_path)
         print("self.pb_tableWidget.itemAt(item.row(), 0).text()", self.projectContext.aside_list[item.row()].st_time_sec)
         wav_path = audio_dir + '/tmp/%.2f.wav' % float(self.projectContext.aside_list[item.row()].st_time_sec)
@@ -654,8 +670,7 @@ class MainWindow(QMainWindow, Ui_MainWindow):
             self.projectContext.refresh_aside(row, text)
             # 更新【字幕旁白】这个tab里的字
             start_time = self.pb_tableWidget.item(int(row), constant.Aside.StartTimeColumn).text()
-            idx = self.projectContext.aside2contentId(Element(str(start_time),0,0,0,0))
-            # self.projectContext.refresh_element(idx, text)
+            idx = self.projectContext.aside_subtitle_2contentId(Element(str(start_time),0,0,0,0))
             self.all_tableWidget.setItem(int(row), constant.Content.ActivateColumn, QTableWidgetItem(text))
     def write2ProjectFromContent(self, item):
         print("write2ProjectFromContent")
@@ -723,4 +738,54 @@ class MainWindow(QMainWindow, Ui_MainWindow):
         # 在【打开工程】操作的时候，设置sld_video的最大值为电影秒数。
         print("打开工程：self.player.duration()", self.player.duration())
         print("设置最大值为：", self.player.duration()/1000 + 1)
-        self.sld_video.setMaximum(self.player.duration()/1000 + 1)
\ No newline at end of file
+        self.sld_video.setMaximum(self.player.duration()/1000 + 1)
+
+    def refresh_tab_slot(self):
+        self.set_table_to_window()
+        self.projectContext.save_project(False)
+
+
+    def operate_slot(self):
+        self.operation_dialog.show()
+
+    def add_line_operation_slot(self, row, start_time, end_time, subtitle, suggest, aside):
+        # 注意，这里需要用同一对象，不能生成多个Element
+        new_element = Element(start_time, end_time, subtitle, suggest, aside)
+        self.projectContext.all_elements.insert(int(row), new_element)
+        if suggest is not None and "插入旁白，推荐字数为" in suggest:
+            idx = 0
+            while idx < len(self.projectContext.aside_list):
+                if float(start_time) < float(self.projectContext.aside_list[idx].st_time_sec):
+                    break
+                idx += 1
+            self.projectContext.aside_list.insert(idx, new_element)
+        else:
+            idx = 0
+            while idx < len(self.projectContext.subtitle_list):
+                if float(start_time) < float(self.projectContext.subtitle_list[idx].st_time_sec):
+                    break
+                idx += 1
+            self.projectContext.subtitle_list.insert(idx, new_element)
+
+        self.prompt_dialog.show_with_msg("操作成功！！请刷新表格查看变化")
+
+
+    def del_line_operation_slot(self, row, start_time, end_time, subtitle, suggest, aside):
+
+        to_be_delete_element = self.projectContext.all_elements[int(row) - 1]
+        if self.projectContext.all_elements[int(row)-1].suggest is not None \
+                and "插入旁白，推荐字数为" in self.projectContext.all_elements[int(row)-1].suggest:
+            for i in range(len(self.projectContext.aside_list)):
+                if to_be_delete_element.equalTo(self.projectContext.aside_list[i]):
+                    self.projectContext.aside_list.pop(i)
+                    break
+        else:
+            for i in range(len(self.projectContext.subtitle_header)):
+                if to_be_delete_element.equalTo(self.projectContext.subtitle_list[i]):
+                    self.projectContext.subtitle_list.pop(i)
+                    break
+
+        self.projectContext.all_elements.pop(int(row)-1)
+
+        self.prompt_dialog.show_with_msg("操作成功！！请刷新表格查看变化")
+

main_window.ui

@@ -515,6 +515,8 @@ QPushButton:pressed {
     <addaction name="action_undo"/>
     <addaction name="action_redo"/>
     <addaction name="action_view_history"/>
+    <addaction name="separator"/>
+    <addaction name="action_operate"/>
    </widget>
    <widget class="QMenu" name="menu_3">
     <property name="title">
@@ -522,6 +524,8 @@ QPushButton:pressed {
     </property>
     <addaction name="actiona_3"/>
     <addaction name="actiona_4"/>
+    <addaction name="separator"/>
+    <addaction name="action_refresh_tab"/>
    </widget>
    <addaction name="menu"/>
    <addaction name="menu_2"/>
@@ -550,7 +554,7 @@ QPushButton:pressed {
   </action>
   <action name="action_save">
    <property name="text">
-    <string>工程保存</string>
+    <string>保存并备份</string>
    </property>
   </action>
   <action name="action_undo">
@@ -578,6 +582,16 @@ QPushButton:pressed {
     <string>history</string>
    </property>
   </action>
+  <action name="action_refresh_tab">
+   <property name="text">
+    <string>刷新且保存表格</string>
+   </property>
+  </action>
+  <action name="action_operate">
+   <property name="text">
+    <string>增删行</string>
+   </property>
+  </action>
  </widget>
  <customwidgets>
   <customwidget>

main_window_ui.py

@@ -293,6 +293,10 @@ class Ui_MainWindow(object):
         self.actiona_4.setObjectName("actiona_4")
         self.action_view_history = QtWidgets.QAction(MainWindow)
         self.action_view_history.setObjectName("action_view_history")
+        self.action_refresh_tab = QtWidgets.QAction(MainWindow)
+        self.action_refresh_tab.setObjectName("action_refresh_tab")
+        self.action_operate = QtWidgets.QAction(MainWindow)
+        self.action_operate.setObjectName("action_operate")
         self.menu.addAction(self.actionxinjian)
         self.menu.addAction(self.action_open_project)
         self.menu.addSeparator()
@@ -302,8 +306,12 @@ class Ui_MainWindow(object):
         self.menu_2.addAction(self.action_undo)
         self.menu_2.addAction(self.action_redo)
         self.menu_2.addAction(self.action_view_history)
+        self.menu_2.addSeparator()
+        self.menu_2.addAction(self.action_operate)
         self.menu_3.addAction(self.actiona_3)
         self.menu_3.addAction(self.actiona_4)
+        self.menu_3.addSeparator()
+        self.menu_3.addAction(self.action_refresh_tab)
         self.menubar.addAction(self.menu.menuAction())
         self.menubar.addAction(self.menu_2.menuAction())
         self.menubar.addAction(self.menu_3.menuAction())
@@ -333,12 +341,14 @@ class Ui_MainWindow(object):
         self.action_open_project.setText(_translate("MainWindow", "打开"))
         self.import_movie.setText(_translate("MainWindow", "视频导入"))
         self.actions.setText(_translate("MainWindow", "内容导出"))
-        self.action_save.setText(_translate("MainWindow", "工程保存"))
+        self.action_save.setText(_translate("MainWindow", "保存并备份"))
         self.action_undo.setText(_translate("MainWindow", "撤销"))
         self.action_redo.setText(_translate("MainWindow", "重做"))
         self.actiona_3.setText(_translate("MainWindow", "旁白区间检测"))
         self.actiona_4.setText(_translate("MainWindow", "旁白音频合成"))
         self.action_view_history.setText(_translate("MainWindow", "history"))
+        self.action_refresh_tab.setText(_translate("MainWindow", "刷新且保存表格"))
+        self.action_operate.setText(_translate("MainWindow", "增删行"))
 
 
 from myVideoWidget import myVideoWidget

management.py

@@ -120,8 +120,11 @@ class ProjectContext:
         self.subtitle_list = []
         self.aside_list = []
         self.all_elements = []
-        self.speaker_info = '晓辰，女，年轻人'
-        self.speaker_speed = '1.00(4字/秒)'
+        f = open("./conf.ini", "r", encoding='utf-8')
+        rl = f.readlines()
+        f.close()
+        self.speaker_info = rl[0].strip()
+        self.speaker_speed = rl[1].strip()
         # 一些常量
         self.header = ["起始时间", "终止时间", "字幕", '建议', '解说脚本']
         self.aside_header = ["起始时间", "终止时间", '建议', '解说脚本']
@@ -145,28 +148,38 @@ class ProjectContext:
         self.history_records = []
         self.records_pos = 0
     def Init(self, project_dir, video_name):
+        # 有的时候路径是 '/F:/out1/test.xlsx'，有的时候是'F:/out1/test.xlsx'
+        if project_dir[0] == '/':
+            project_dir = project_dir[1:]
         self.project_base_dir = project_dir
         # self.video_path = os.path.join(project_dir, video_name)
-        self.video_path = project_dir[1:] + "/" + video_name
+        self.video_path = project_dir + "/" + video_name
+        print("video_pathvideo_path: ", self.video_path)
         self.excel_path = replace_path_suffix(self.video_path, ".xlsx")
 
     # def Init(self, project_dir, video_path, excel_path):
     #     self.project_base_dir = project_dir
     #     self.video_path = video_path
     #     self.excel_path = excel_path
+    def save_conf(self):
+        with open('./conf.ini', 'w', encoding='utf-8') as f:
+            f.writelines([self.speaker_info + '\n', self.speaker_speed])
+
     def setVideoPath(self, video_path):
         self.video_path = video_path
     def setExcelPath(self, excel_path):
         self.excel_path = excel_path
 
     # 目前只是把excel保存到文件中
-    # 先备份文件，再覆盖主文件
-    def save_project(self) -> str:
+    # 先备份文件，再覆盖主文件，可选是否需要备份，默认需要备份
+    def save_project(self, need_save_new: bool=False) -> str:
         # all_element = sorted(all_element, key=lambda x: float(x.st_time_sec))
-        new_excel_path = replace_path_suffix(self.excel_path, datetime.datetime.now().strftime('%Y%m%d%H%M%S')+'.xlsx')
-        err_info = save_excel_to_to_path(self.all_elements, new_excel_path, self.header, self.excel_sheet_name)
-        if err_info != None:
-            return err_info
+        print("current excel_path:", self.excel_path)
+        if need_save_new:
+            new_excel_path = replace_path_suffix(self.excel_path, datetime.datetime.now().strftime('%Y%m%d%H%M%S')+'.xlsx')
+            err_info = save_excel_to_to_path(self.all_elements, new_excel_path, self.header, self.excel_sheet_name)
+            if err_info != None:
+                return err_info
         err_info = save_excel_to_to_path(self.all_elements, self.excel_path, self.header, self.excel_sheet_name)
         if err_info != None:
             return err_info
@@ -229,7 +242,8 @@ class ProjectContext:
         self.records_pos += 1
         return res
 
-    def aside2contentId(self, aside_element: Element)->int:
+    # 把【字幕id】或者【旁白id】转化成【内容id】
+    def aside_subtitle_2contentId(self, aside_element: Element)->int:
         for i in range(len(self.all_elements)):
             if aside_element.equalTo(self.all_elements[i]):
                 return i

narratage_detection.py

@@ -11,9 +11,9 @@
 """
 import os.path
 import argparse
+from main_window import MainWindow
 
-
-def detect(video_path: str, start_time: float, end_time: float, book_path: str, state=None, subtitle: int = 0):
+def detect(video_path: str, start_time: float, end_time: float, book_path: str, state=None, subtitle: int = 0, mainWindow: MainWindow=None):
     """字幕及旁白区间检测
 
     Args:
@@ -44,10 +44,10 @@ def detect(video_path: str, start_time: float, end_time: float, book_path: str,
 
     if has_subtitle:
         from detect_with_ocr import detect_with_ocr
-        detect_with_ocr(video_path, book_path, start_time, end_time, state)
-    else:
-        from detect_with_asr import detect_with_asr
-        detect_with_asr(video_path, book_path, start_time, end_time, state)
+        detect_with_ocr(video_path, book_path, start_time, end_time, state, mainWindow)
+    # else:
+    #     from detect_with_asr import detect_with_asr
+    #     detect_with_asr(video_path, book_path, start_time, end_time, state)
 
 
 if __name__ == '__main__':
@@ -64,4 +64,4 @@ if __name__ == '__main__':
 
     args = parser.parse_args()
 
-    detect(args.video_path, args.start_time, args.end_time, args.book_path)
+    detect(args.video_path, args.start_time, args.end_time, args.book_path,None)

operation_dialog.py

+import sys
+import os
+from PyQt5.QtCore import *;
+from PyQt5.QtGui import *;
+from PyQt5.QtWidgets import *;
+
+from operation_dialog_ui import Ui_Dialog
+from utils import validate_and_get_filepath, replace_path_suffix
+
+#todo 注意，删除行，添加行，暂不支持【撤销与重做】功能！！！
+class Operation_Dialog(QDialog, Ui_Dialog):
+
+    #开始检测信号，传参分别是movie路径和输出表格路径
+    start_add_signal = pyqtSignal(str, str, str, str, str, str)
+    start_del_signal = pyqtSignal(str, str, str, str, str, str)
+    def __init__(self, mainWindow):
+        super(Operation_Dialog, self).__init__()
+        self.setupUi(self)
+        self.setWindowTitle("操作表格")
+        self.mainWindow = mainWindow
+
+        self.pushButton.clicked.connect(self.check_validate_slot)
+        self.pushButton_2.clicked.connect(self.remake_slot)
+        self.buttonBox.setEnabled(False)
+        self.buttonBox.button(QDialogButtonBox.StandardButton.Ok).clicked.connect(self.start_operation_slot)
+        # 字幕/旁白 选择框
+        self.comboBox.currentIndexChanged.connect(self.zmpb_change_slot)
+        # 增加一行/删除一行 选择框
+        self.comboBox_2.currentIndexChanged.connect(self.adddel_change_slot)
+
+        self.lineEdits = [self.lineEdit, self.lineEdit_2, self.lineEdit_3, self.lineEdit_4, self.lineEdit_5, self.lineEdit_6]
+
+        self.zmpb_change_slot()
+        self.adddel_change_slot()
+
+    def zmpb_change_slot(self):
+        # 如果是删除，则直接return
+        if self.comboBox_2.currentText() == "删除一行":
+            return
+
+        self.set_all_user_component_status(True)
+        if self.comboBox.currentText() == "字幕":
+            self.lineEdit_5.setEnabled(False)
+            self.lineEdit_6.setEnabled(False)
+        else:
+            self.lineEdit_3.setEnabled(False)
+            self.lineEdit_4.setEnabled(False)
+
+    # 如果是删除，则只需要【行数】即可
+    def adddel_change_slot(self):
+        if self.comboBox_2.currentText() == "增加一行":
+            self.zmpb_change_slot()
+        else:
+            for i in range(1,len(self.lineEdits)):
+                self.lineEdits[i].setEnabled(False)
+
+    # 修改完后需要重新检测
+    def remake_slot(self):
+        self.buttonBox.setEnabled(False)
+        self.set_all_user_component_status(True)
+
+    def check_validate_slot(self):
+        # 校验行数
+        rowCount = self.mainWindow.all_tableWidget.rowCount()
+        try:
+            cnt = int(self.lineEdit.text())
+            assert cnt <= rowCount
+        except Exception as e:
+            self.mainWindow.prompt_dialog.show_with_msg("校验失败！总行数为[%d],你的输入为[%s]!!"%(rowCount, self.lineEdit.text()))
+            return
+
+        # 这些是只有【add】才需要检测的
+        if self.comboBox_2.currentText() == "增加一行":
+            #校验起始时间、结束时间
+            start_time_f, end_time_f = 0.0, 0.0
+            try:
+                start_time_f = float(self.lineEdit_2.text())
+                if self.comboBox.currentText() == "字幕":
+                    end_time_f = float(self.lineEdit_3.text())
+                    assert start_time_f < end_time_f
+            except Exception as e:
+                self.mainWindow.prompt_dialog.show_with_msg("校验失败！起始时间或结束时间输入有误!!" )
+                return
+
+            # 校验推荐字数
+            if self.comboBox.currentText() == "旁白":
+                try:
+                    suggest_words_count = int(self.lineEdit_5.text())
+                    assert suggest_words_count <= 100
+                except Exception as e:
+                    self.mainWindow.prompt_dialog.show_with_msg("校验失败！推荐字数填入有误!!")
+                    return
+
+        # 检测通过
+        self.mainWindow.prompt_dialog.show_with_msg("校验成功!!")
+        self.buttonBox.setEnabled(True)
+        self.set_all_user_component_status(False)
+
+
+    def set_all_user_component_status(self, status: bool):
+        for lineEdit in self.lineEdits:
+            lineEdit.setEnabled(status)
+        self.comboBox.setEnabled(status)
+        self.comboBox_2.setEnabled(status)
+
+    def start_operation_slot(self):
+
+        row, start_time, end_time, subtitle, suggest, aside = [x.text() for x in self.lineEdits]
+
+        if self.comboBox.currentText() == "字幕":
+            suggest = ""
+            aside = ""
+        else: # 如果是旁白
+            end_time = ""
+            subtitle = ""
+            suggest = "插入旁白，推荐字数为" + suggest
+
+        # 别忘复原
+        self.buttonBox.setEnabled(False)
+        self.zmpb_change_slot()
+        self.adddel_change_slot()
+
+        # 根据增删两种操作，分别触发不同信号。
+        if self.comboBox_2.currentText() == "增加一行":
+            self.start_add_signal.emit(row, start_time, end_time, subtitle, suggest, aside)
+        else:
+            self.start_del_signal.emit(row, start_time, end_time, subtitle, suggest, aside)
+
+if __name__ == '__main__':
+    app = QApplication(sys.argv)
+    app.setWindowIcon(QIcon("./images/eagle_2.ico"))
+    dialog = Operation_Dialog()
+    dialog.show()
+    sys.exit(app.exec_())
\ No newline at end of file

operation_dialog.ui

+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>Dialog</class>
+ <widget class="QDialog" name="Dialog">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>635</width>
+    <height>395</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Dialog</string>
+  </property>
+  <widget class="QDialogButtonBox" name="buttonBox">
+   <property name="enabled">
+    <bool>false</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>470</x>
+     <y>340</y>
+     <width>101</width>
+     <height>32</height>
+    </rect>
+   </property>
+   <property name="toolTip">
+    <string/>
+   </property>
+   <property name="toolTipDuration">
+    <number>-1</number>
+   </property>
+   <property name="orientation">
+    <enum>Qt::Horizontal</enum>
+   </property>
+   <property name="standardButtons">
+    <set>QDialogButtonBox::Ok</set>
+   </property>
+   <property name="centerButtons">
+    <bool>false</bool>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label">
+   <property name="geometry">
+    <rect>
+     <x>60</x>
+     <y>70</y>
+     <width>81</width>
+     <height>20</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>我想操作第</string>
+   </property>
+  </widget>
+  <widget class="QLineEdit" name="lineEdit">
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>70</y>
+     <width>101</width>
+     <height>21</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_2">
+   <property name="geometry">
+    <rect>
+     <x>250</x>
+     <y>70</y>
+     <width>311</width>
+     <height>21</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>行（如果操作是增加，则在该行后面增加）</string>
+   </property>
+  </widget>
+  <widget class="QLineEdit" name="lineEdit_2">
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>120</y>
+     <width>101</width>
+     <height>21</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_3">
+   <property name="geometry">
+    <rect>
+     <x>60</x>
+     <y>120</y>
+     <width>71</width>
+     <height>16</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>起始时间：</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_4">
+   <property name="geometry">
+    <rect>
+     <x>60</x>
+     <y>170</y>
+     <width>71</width>
+     <height>16</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>结束时间：</string>
+   </property>
+  </widget>
+  <widget class="QLineEdit" name="lineEdit_3">
+   <property name="enabled">
+    <bool>true</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>170</y>
+     <width>101</width>
+     <height>21</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QLineEdit" name="lineEdit_4">
+   <property name="enabled">
+    <bool>true</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>220</y>
+     <width>231</width>
+     <height>21</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QComboBox" name="comboBox">
+   <property name="enabled">
+    <bool>true</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>20</y>
+     <width>87</width>
+     <height>22</height>
+    </rect>
+   </property>
+   <property name="editable">
+    <bool>false</bool>
+   </property>
+   <item>
+    <property name="text">
+     <string>字幕</string>
+    </property>
+   </item>
+   <item>
+    <property name="text">
+     <string>旁白</string>
+    </property>
+   </item>
+  </widget>
+  <widget class="QComboBox" name="comboBox_2">
+   <property name="geometry">
+    <rect>
+     <x>260</x>
+     <y>20</y>
+     <width>87</width>
+     <height>22</height>
+    </rect>
+   </property>
+   <item>
+    <property name="text">
+     <string>增加一行</string>
+    </property>
+   </item>
+   <item>
+    <property name="text">
+     <string>删除一行</string>
+    </property>
+   </item>
+  </widget>
+  <widget class="QLineEdit" name="lineEdit_5">
+   <property name="enabled">
+    <bool>true</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>260</y>
+     <width>101</width>
+     <height>21</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QLineEdit" name="lineEdit_6">
+   <property name="enabled">
+    <bool>true</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>140</x>
+     <y>300</y>
+     <width>231</width>
+     <height>21</height>
+    </rect>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_5">
+   <property name="geometry">
+    <rect>
+     <x>60</x>
+     <y>220</y>
+     <width>71</width>
+     <height>16</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>字幕：</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_6">
+   <property name="geometry">
+    <rect>
+     <x>60</x>
+     <y>260</y>
+     <width>71</width>
+     <height>16</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>推荐字数：</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_7">
+   <property name="geometry">
+    <rect>
+     <x>60</x>
+     <y>300</y>
+     <width>71</width>
+     <height>16</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>旁白：</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_8">
+   <property name="geometry">
+    <rect>
+     <x>250</x>
+     <y>120</y>
+     <width>251</width>
+     <height>20</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>*请填数字，最多保留两位小数</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_9">
+   <property name="geometry">
+    <rect>
+     <x>250</x>
+     <y>170</y>
+     <width>251</width>
+     <height>20</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>*请填数字，最多保留两位小数</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_10">
+   <property name="geometry">
+    <rect>
+     <x>380</x>
+     <y>220</y>
+     <width>81</width>
+     <height>20</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>*请填文字</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_11">
+   <property name="geometry">
+    <rect>
+     <x>380</x>
+     <y>300</y>
+     <width>81</width>
+     <height>20</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>*请填文字</string>
+   </property>
+  </widget>
+  <widget class="QLabel" name="label_12">
+   <property name="geometry">
+    <rect>
+     <x>250</x>
+     <y>260</y>
+     <width>251</width>
+     <height>20</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>*请填数字，必须是不超过100的正整数</string>
+   </property>
+  </widget>
+  <widget class="QPushButton" name="pushButton">
+   <property name="geometry">
+    <rect>
+     <x>350</x>
+     <y>340</y>
+     <width>93</width>
+     <height>28</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>检测</string>
+   </property>
+  </widget>
+  <widget class="QPushButton" name="pushButton_2">
+   <property name="geometry">
+    <rect>
+     <x>230</x>
+     <y>340</y>
+     <width>93</width>
+     <height>28</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>修改</string>
+   </property>
+  </widget>
+ </widget>
+ <resources/>
+ <connections>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>rejected()</signal>
+   <receiver>Dialog</receiver>
+   <slot>reject()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>316</x>
+     <y>260</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>286</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>accepted()</signal>
+   <receiver>Dialog</receiver>
+   <slot>accept()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>248</x>
+     <y>254</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>157</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+ </connections>
+</ui>

operation_dialog_ui.py

+# -*- coding: utf-8 -*-
+
+# Form implementation generated from reading ui file 'operation_dialog.ui'
+#
+# Created by: PyQt5 UI code generator 5.12
+#
+# WARNING! All changes made in this file will be lost!
+
+from PyQt5 import QtCore, QtGui, QtWidgets
+
+
+class Ui_Dialog(object):
+    def setupUi(self, Dialog):
+        Dialog.setObjectName("Dialog")
+        Dialog.resize(635, 395)
+        self.buttonBox = QtWidgets.QDialogButtonBox(Dialog)
+        self.buttonBox.setEnabled(False)
+        self.buttonBox.setGeometry(QtCore.QRect(470, 340, 101, 32))
+        self.buttonBox.setToolTip("")
+        self.buttonBox.setToolTipDuration(-1)
+        self.buttonBox.setOrientation(QtCore.Qt.Horizontal)
+        self.buttonBox.setStandardButtons(QtWidgets.QDialogButtonBox.Ok)
+        self.buttonBox.setCenterButtons(False)
+        self.buttonBox.setObjectName("buttonBox")
+        self.label = QtWidgets.QLabel(Dialog)
+        self.label.setGeometry(QtCore.QRect(60, 70, 81, 20))
+        self.label.setObjectName("label")
+        self.lineEdit = QtWidgets.QLineEdit(Dialog)
+        self.lineEdit.setGeometry(QtCore.QRect(140, 70, 101, 21))
+        self.lineEdit.setObjectName("lineEdit")
+        self.label_2 = QtWidgets.QLabel(Dialog)
+        self.label_2.setGeometry(QtCore.QRect(250, 70, 311, 21))
+        self.label_2.setObjectName("label_2")
+        self.lineEdit_2 = QtWidgets.QLineEdit(Dialog)
+        self.lineEdit_2.setGeometry(QtCore.QRect(140, 120, 101, 21))
+        self.lineEdit_2.setObjectName("lineEdit_2")
+        self.label_3 = QtWidgets.QLabel(Dialog)
+        self.label_3.setGeometry(QtCore.QRect(60, 120, 71, 16))
+        self.label_3.setObjectName("label_3")
+        self.label_4 = QtWidgets.QLabel(Dialog)
+        self.label_4.setGeometry(QtCore.QRect(60, 170, 71, 16))
+        self.label_4.setObjectName("label_4")
+        self.lineEdit_3 = QtWidgets.QLineEdit(Dialog)
+        self.lineEdit_3.setEnabled(True)
+        self.lineEdit_3.setGeometry(QtCore.QRect(140, 170, 101, 21))
+        self.lineEdit_3.setObjectName("lineEdit_3")
+        self.lineEdit_4 = QtWidgets.QLineEdit(Dialog)
+        self.lineEdit_4.setEnabled(True)
+        self.lineEdit_4.setGeometry(QtCore.QRect(140, 220, 231, 21))
+        self.lineEdit_4.setObjectName("lineEdit_4")
+        self.comboBox = QtWidgets.QComboBox(Dialog)
+        self.comboBox.setEnabled(True)
+        self.comboBox.setGeometry(QtCore.QRect(140, 20, 87, 22))
+        self.comboBox.setEditable(False)
+        self.comboBox.setObjectName("comboBox")
+        self.comboBox.addItem("")
+        self.comboBox.addItem("")
+        self.comboBox_2 = QtWidgets.QComboBox(Dialog)
+        self.comboBox_2.setGeometry(QtCore.QRect(260, 20, 87, 22))
+        self.comboBox_2.setObjectName("comboBox_2")
+        self.comboBox_2.addItem("")
+        self.comboBox_2.addItem("")
+        self.lineEdit_5 = QtWidgets.QLineEdit(Dialog)
+        self.lineEdit_5.setEnabled(True)
+        self.lineEdit_5.setGeometry(QtCore.QRect(140, 260, 101, 21))
+        self.lineEdit_5.setObjectName("lineEdit_5")
+        self.lineEdit_6 = QtWidgets.QLineEdit(Dialog)
+        self.lineEdit_6.setEnabled(True)
+        self.lineEdit_6.setGeometry(QtCore.QRect(140, 300, 231, 21))
+        self.lineEdit_6.setObjectName("lineEdit_6")
+        self.label_5 = QtWidgets.QLabel(Dialog)
+        self.label_5.setGeometry(QtCore.QRect(60, 220, 71, 16))
+        self.label_5.setObjectName("label_5")
+        self.label_6 = QtWidgets.QLabel(Dialog)
+        self.label_6.setGeometry(QtCore.QRect(60, 260, 71, 16))
+        self.label_6.setObjectName("label_6")
+        self.label_7 = QtWidgets.QLabel(Dialog)
+        self.label_7.setGeometry(QtCore.QRect(60, 300, 71, 16))
+        self.label_7.setObjectName("label_7")
+        self.label_8 = QtWidgets.QLabel(Dialog)
+        self.label_8.setGeometry(QtCore.QRect(250, 120, 251, 20))
+        self.label_8.setObjectName("label_8")
+        self.label_9 = QtWidgets.QLabel(Dialog)
+        self.label_9.setGeometry(QtCore.QRect(250, 170, 251, 20))
+        self.label_9.setObjectName("label_9")
+        self.label_10 = QtWidgets.QLabel(Dialog)
+        self.label_10.setGeometry(QtCore.QRect(380, 220, 81, 20))
+        self.label_10.setObjectName("label_10")
+        self.label_11 = QtWidgets.QLabel(Dialog)
+        self.label_11.setGeometry(QtCore.QRect(380, 300, 81, 20))
+        self.label_11.setObjectName("label_11")
+        self.label_12 = QtWidgets.QLabel(Dialog)
+        self.label_12.setGeometry(QtCore.QRect(250, 260, 251, 20))
+        self.label_12.setObjectName("label_12")
+        self.pushButton = QtWidgets.QPushButton(Dialog)
+        self.pushButton.setGeometry(QtCore.QRect(350, 340, 93, 28))
+        self.pushButton.setObjectName("pushButton")
+        self.pushButton_2 = QtWidgets.QPushButton(Dialog)
+        self.pushButton_2.setGeometry(QtCore.QRect(230, 340, 93, 28))
+        self.pushButton_2.setObjectName("pushButton_2")
+
+        self.retranslateUi(Dialog)
+        self.buttonBox.rejected.connect(Dialog.reject)
+        self.buttonBox.accepted.connect(Dialog.accept)
+        QtCore.QMetaObject.connectSlotsByName(Dialog)
+
+    def retranslateUi(self, Dialog):
+        _translate = QtCore.QCoreApplication.translate
+        Dialog.setWindowTitle(_translate("Dialog", "Dialog"))
+        self.label.setText(_translate("Dialog", "我想操作第"))
+        self.label_2.setText(_translate("Dialog", "行（如果操作是增加，则在该行后面增加）"))
+        self.label_3.setText(_translate("Dialog", "起始时间："))
+        self.label_4.setText(_translate("Dialog", "结束时间："))
+        self.comboBox.setItemText(0, _translate("Dialog", "字幕"))
+        self.comboBox.setItemText(1, _translate("Dialog", "旁白"))
+        self.comboBox_2.setItemText(0, _translate("Dialog", "增加一行"))
+        self.comboBox_2.setItemText(1, _translate("Dialog", "删除一行"))
+        self.label_5.setText(_translate("Dialog", "字幕："))
+        self.label_6.setText(_translate("Dialog", "推荐字数："))
+        self.label_7.setText(_translate("Dialog", "旁白："))
+        self.label_8.setText(_translate("Dialog", "*请填数字，最多保留两位小数"))
+        self.label_9.setText(_translate("Dialog", "*请填数字，最多保留两位小数"))
+        self.label_10.setText(_translate("Dialog", "*请填文字"))
+        self.label_11.setText(_translate("Dialog", "*请填文字"))
+        self.label_12.setText(_translate("Dialog", "*请填数字，必须是不超过100的正整数"))
+        self.pushButton.setText(_translate("Dialog", "检测"))
+        self.pushButton_2.setText(_translate("Dialog", "修改"))
+
+

setting_dialog.py

@@ -7,6 +7,9 @@ from PyQt5.QtWidgets import *;
 from setting_dialog_ui import Ui_Dialog
 from utils import validate_and_get_filepath, replace_path_suffix
 
+import winsound
+
+audioPlayed = winsound.PlaySound(None, winsound.SND_NODEFAULT)
 
 
 class Setting_Dialog(QDialog, Ui_Dialog):
@@ -23,18 +26,62 @@ class Setting_Dialog(QDialog, Ui_Dialog):
         li = self.projectContext.get_all_speaker_info()
         for i in li:
             self.comboBox.addItem(i)
-            # self.comboBox.addItem('晓秋，女，年轻人')
-        self.comboBox_2.addItems(["1.00(4字/秒)", "1.10(4.5字/秒)", "1.25(5字/秒)", "1.50(6字/秒)", "1.75(7字/秒)", "2.00(8字/秒)", "2.50(10字/秒)"])
+        li_2 = ["1.00(4字/秒)", "1.10(4.5字/秒)", "1.25(5字/秒)", "1.50(6字/秒)", "1.75(7字/秒)", "2.00(8字/秒)", "2.50(10字/秒)"]
+        self.comboBox_2.addItems(li_2)
+
+        self.comboBox.setCurrentIndex(li.index(self.projectContext.speaker_info))
+        self.comboBox_2.setCurrentIndex(li_2.index(self.projectContext.speaker_speed))
 
         self.comboBox.currentIndexChanged.connect(self.speaker_change_slot)
         self.comboBox_2.currentIndexChanged.connect(self.speed_change_slot)
 
+        self.pushButton.clicked.connect(self.play_audio_slot)
+
+
     def speaker_change_slot(self):
         self.projectContext.speaker_info = self.comboBox.currentText()
+        self.projectContext.save_conf()
         # print("self.projectContext.speaker_info:", self.projectContext.speaker_info)
     def speed_change_slot(self):
         self.projectContext.speaker_speed = self.comboBox_2.currentText()
+        self.projectContext.save_conf()
+
+    def play_audio_slot(self):
+        """播放说话人的样例音频
+
+            根据用户选择的说话人更新对应样例音频
+            停止上一个说话人的音频
+            播放当前说话人的音频
+        """
+        def f():
+            chosenSpeaker = self.projectContext.choose_speaker(self.projectContext.speaker_info.split("，")[0])
+            # 停止音频
+            global audioPlayed
+            winsound.PlaySound(audioPlayed, winsound.SND_PURGE)
+            # 播放音频
+            audioPlayed = winsound.PlaySound(chosenSpeaker.voice_example, winsound.SND_ASYNC)
+
+        thread_it(f, name="playAudio")
+    # 重写关闭窗口事件，使得可以停止播放样例视频
+    def closeEvent(self, event):
+        global audioPlayed
+        winsound.PlaySound(audioPlayed, winsound.SND_PURGE)
+        event.accept()
+def thread_it(func, *args, name):
+    """创建守护线程
 
+    Args:
+        func: 待执行的函数名
+        args: 函数所需的参数
+        name: 线程名
+    """
+    # 创建线程
+    import threading
+    t = threading.Thread(target=func, args=args, name=name)
+    # 守护
+    t.setDaemon(True)
+    # 启动
+    t.start()
 if __name__ == '__main__':
     app = QApplication(sys.argv)
     app.setWindowIcon(QIcon("./images/eagle_2.ico"))

setting_dialog.ui

@@ -65,6 +65,19 @@
     <string/>
    </property>
   </widget>
+  <widget class="QPushButton" name="pushButton">
+   <property name="geometry">
+    <rect>
+     <x>350</x>
+     <y>140</y>
+     <width>121</width>
+     <height>71</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>播放样例音频</string>
+   </property>
+  </widget>
  </widget>
  <resources/>
  <connections/>

setting_dialog_ui.py

@@ -27,6 +27,9 @@ class Ui_Dialog(object):
         self.comboBox_2.setGeometry(QtCore.QRect(130, 190, 151, 31))
         self.comboBox_2.setCurrentText("")
         self.comboBox_2.setObjectName("comboBox_2")
+        self.pushButton = QtWidgets.QPushButton(Dialog)
+        self.pushButton.setGeometry(QtCore.QRect(350, 140, 121, 71))
+        self.pushButton.setObjectName("pushButton")
 
         self.retranslateUi(Dialog)
         QtCore.QMetaObject.connectSlotsByName(Dialog)
@@ -36,5 +39,6 @@ class Ui_Dialog(object):
         Dialog.setWindowTitle(_translate("Dialog", "Dialog"))
         self.label_3.setText(_translate("Dialog", "旁白说话人："))
         self.label_4.setText(_translate("Dialog", "旁白语速："))
+        self.pushButton.setText(_translate("Dialog", "播放样例音频"))
 
 

speech_synthesis.py

@@ -100,7 +100,9 @@ def speech_synthesis(text: str, output_file: str, speaker: Speaker, speed: float
     speech_config.speech_synthesis_voice_name = speaker.speaker_code
 
     # 先把合成的语音文件输出得到tmp.wav中，便于可能的调速需求
-
+    if not os.path.exists(os.path.dirname(audio_path)):  # 如果路径不存在
+        print("路径不存在，创建:", os.path.dirname(audio_path))
+        os.makedirs(os.path.dirname(audio_path))
     audio_config = AudioOutputConfig(filename=audio_path)
     synthesizer = SpeechSynthesizer(
         speech_config=speech_config, audio_config=audio_config)

start.py

@@ -10,6 +10,7 @@ from main_window import MainWindow
 
 if __name__ == '__main__':
     try:
+        QCoreApplication.setAttribute(Qt.AA_EnableHighDpiScaling)
         app = QApplication(sys.argv)
         app.setWindowIcon(QIcon("./images/eagle_2.ico"))
         mainWindow = MainWindow()