0604

0604/realtime_transcriber.py

@@ -1,7 +1,4 @@
-
-# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
 import websocket
-import datetime
 import hashlib
 import base64
 import hmac
@@ -15,6 +12,9 @@ from time import mktime
 import _thread as thread
 import pyaudio
 
+class RealtimeTranscriber:
+    pass
+
 STATUS_FIRST_FRAME = 0  # 第一帧的标识
 STATUS_CONTINUE_FRAME = 1  # 中间帧标识
 STATUS_LAST_FRAME = 2  # 最后一帧的标识
@@ -83,7 +83,7 @@ def on_message(ws, message):
             for i in data:
                 for w in i["cw"]:
                     result += w["w"]
-            if result != "。" or result == ".>" or result == ' .。' or result == ' 。':
+            if result == "。" or result == ".。" or result == ' .。' or result == ' 。':
                 pass
             else:
                 t.insert(END,result)
@@ -184,5 +184,7 @@ root =Tk()
 t=Text(root)
 t.pack()
 
-tkinter.Button(root,text='go',command=lambda :thread_it(run,)).pack()
+tkinter.Button(root,text='识别',command=lambda :thread_it(run,)).pack()
 root.mainloop()
+
+

0604/yuyin.py

@@ -4,6 +4,7 @@ import speech_recognition as sr
 from tkinter import filedialog
 import threading
 
+
 engine = pyttsx3.init()
 
 def center_window(window, width=200, height=150):
@@ -100,10 +101,9 @@ def recognize_audio_from_file():
         file_path = filedialog.askopenfilename(filetypes=[("Audio Files", "*.wav")])
         if file_path:
             r = sr.Recognizer()
-            r.language = 'zh-CN'
             with sr.AudioFile(file_path) as source:
                 audio_data = r.record(source)
-                text = r.recognize_sphinx(audio_data)
+                text = r.recognize_sphinx(audio_data,language='zh-CN')
                 window.update_idletasks()  # 更新窗口以避免同步问题
                 text_entry.delete(1.0, tk.END)  # 清空文本框
                 text_entry.insert(tk.END, f"{text}")
@@ -117,37 +117,6 @@ def recognize_audio_from_file():
 
 
 
-def recognize_audio_realtime(parent):
-    window = tk.Toplevel(parent)
-    window.title("实时转写")
-
-    center_window(window)
-    # 初始化识别器
-    r = sr.Recognizer()
-    # 使用麦克风作为源
-    mic = sr.Microphone()
-
-    # 调整能量阈值和监听时间以适应不同环境
-    with mic as source:
-        r.adjust_for_ambient_noise(source)
-        print("请开始说话...")
-
-        # 这里简化处理，实际实时转写可能需要循环监听并处理数据块
-        audio = r.listen(source, timeout=5)  # 例如，监听5秒
-
-    try:
-        # 尝试识别
-        text = r.recognize_google(audio, language='zh-CN')
-        text_entry.delete(1.0, tk.END)  # 清空文本框
-        text_entry.insert(tk.END, text)  # 插入识别的文本
-        result_label.config(text="实时语音已转换为文本")
-    except sr.WaitTimeoutError:
-        result_label.config(text="未检测到语音输入")
-    except sr.UnknownValueError:
-        result_label.config(text="无法识别音频中的内容")
-    except sr.RequestError as e:
-        result_label.config(text=f"识别服务请求错误; {e}")
-
 def main():
     window = tk.Tk()
     window.title("选择界面")
@@ -162,9 +131,7 @@ def main():
     audio_recognition_button = tk.Button(window, text="音频文件识别", command=lambda: create_audio_recognition_window(window))
     audio_recognition_button.pack(padx=10,pady=10)
 
-    # 创建并配置跳转到实时语音识别窗口的按钮
-    audio_button = tk.Button(window, text="实时转写",command=lambda: recognize_audio_realtime(window))
-    audio_button.pack(padx=10,pady=10)
+
 
     center_window(window)
 

1.py

@@ -1,92 +0,0 @@
-import tkinter as tk
-from tkinter import ttk
-import speech_recognition as sr
-import pyttsx3
-
-# 初始化文本转语音引擎
-engine = pyttsx3.init()
-
-
-def text_to_speech():
-    text = text_input.get("1.0", "end-1c")
-    engine.say(text)
-    engine.runAndWait()
-
-
-def speech_to_text():
-    # 初始化识别器
-    r = sr.Recognizer()
-
-    with sr.Microphone() as source:
-        print("请说话:")
-        audio = r.listen(source)
-
-    try:
-        text = r.recognize_google(audio, language='zh-CN')
-        text_output.delete("1.0", tk.END)
-        text_output.insert(tk.END, text)
-    except sr.UnknownValueError:
-        print("Google Speech Recognition无法理解音频")
-    except sr.RequestError as e:
-        print(f"无法从Google Speech Recognition服务请求结果; {e}")
-
-
-def real_time_transcription():
-    # 这里简化处理，实际应用中需要一个循环监听并实时转写
-
-    print("实时转写功能尚未实现，请手动调用speech_to_text进行单次转写")
-
-
-def switch_frame(frame):
-    frame.tkraise()
-
-
-# 创建主窗口
-root = tk.Tk()
-root.title("语音识别与转换系统")
-
-# 创建一个容器来放置不同的Frame
-container = ttk.Frame(root)
-container.pack(side="top", fill="both", expand=True)
-
-# 创建不同的Frame对应不同功能
-frame_text_to_speech = ttk.Frame(container)
-frame_speech_to_text = ttk.Frame(container)
-frame_real_time = ttk.Frame(container)
-
-# 在每个Frame中添加对应的功能组件
-# 文本转语音Frame
-ttk.Label(frame_text_to_speech, text="请输入要转换为语音的文本:").pack()
-text_input = tk.Text(frame_text_to_speech, height=20)
-text_input.pack()
-ttk.Button(frame_text_to_speech, text="转换", command=text_to_speech).pack()
-
-# 语音转文本Frame
-ttk.Label(frame_speech_to_text, text="请点击下方按钮开始语音识别:").pack()
-ttk.Button(frame_speech_to_text, text="开始识别", command=speech_to_text).pack()
-text_output = tk.Text(frame_speech_to_text, height=20)
-text_output.pack()
-
-# 实时转写Frame（简化示意）
-ttk.Label(frame_real_time, text="实时转写功能界面（待实现）").pack()
-ttk.Button(frame_real_time, text="返回", command=lambda: switch_frame(container)).pack()
-
-# 将所有Frame添加到容器中
-for frame in (frame_text_to_speech, frame_speech_to_text, frame_real_time):
-    frame.grid(row=0, column=0, sticky="nsew")
-
-switch_frame(frame_text_to_speech)  # 默认显示文本转语音界面
-
-# 创建顶部菜单进行功能切换
-menu = tk.Menu(root)
-
-root.config(menu=menu)
-
-sub_menu = tk.Menu(menu, tearoff=0)
-
-menu.add_cascade(label="功能选择", menu=sub_menu)
-sub_menu.add_command(label="文本转语音", command=lambda: switch_frame(frame_text_to_speech))
-sub_menu.add_command(label="语音转文本", command=lambda: switch_frame(frame_speech_to_text))
-sub_menu.add_command(label="实时转写", command=lambda: switch_frame(frame_real_time))
-
-root.mainloop()

README.md

@@ -1,2 +0,0 @@
-# yuyin
-

转语音.py

@@ -1,45 +0,0 @@
-import tkinter as tk
-from tkinter import ttk
-import pyttsx3
-
-
-def text_to_speech():
-    engine = pyttsx3.init()
-    text = text_entry.get("1.0", "end-1c")  # 获取文本框中的文本
-    engine.say(text)
-    speed = speed_slider.get()
-    engine.setProperty('rate', speed)
-    engine.runAndWait()
-
-
-def main():
-    global text_entry
-
-    # 创建主窗口
-    app = tk.Tk()
-    app.title("文本转语音")
-
-
-
-    speed_slider = ttk.Scale(app, from_=50, to=200, orient=tk.HORIZONTAL)
-    speed_slider.set(120)  # 默认语速
-    speed_slider.pack()
-
-    # 创建一个标签，用于提示输入文本
-    label = tk.Label(app, text="请输入文字:")
-    label.pack(pady=10)
-
-    # 创建一个文本框，用于用户输入
-    text_entry = tk.Text(app, height=10)
-    text_entry.pack()
-
-    # 创建一个按钮，点击时调用text_to_speech函数
-    convert_button = tk.Button(app, text="识别", command=text_to_speech)
-    convert_button.pack(pady=10)
-
-    # 运行主循环
-    app.mainloop()
-
-
-if __name__ == "__main__":
-    main()