适配为纯英文版本

app.py

@@ -45,11 +45,11 @@ custom_css = """
 TASK_PROMPT_MAPPING = {
     "ASR (Automatic Speech Recognition)": "执行语音识别任务，将音频转换为文字。",
     "SRWT (Speech Recognition with Timestamps)": "请转录音频内容，并为每个英文词汇及其对应的中文翻译标注出精确到0.1秒的起止时间，时间范围用<>括起来。",
-    "VED (Vocal Event Detection)(类别:laugh，cough，cry，screaming，sigh，throat clearing，sneeze，other)": "请将音频转录为文字记录，并在记录末尾标注<音频事件>标签，音频事件共8种：laugh，cough，cry，screaming，sigh，throat clearing，sneeze，other。",
-    "SER (Speech Emotion Recognition)(类别:sad，anger，neutral，happy，surprise，fear，disgust，和other)": "请将音频内容转录成文字记录，并在记录末尾标注<情感>标签，情感共8种：sad，anger，neutral，happy，surprise，fear，disgust，和other。",
-    "SSR (Speaking Style Recognition)(类别:新闻科普，恐怖故事，童话故事，客服，诗歌散文，有声书，日常口语，其他)": "请将音频内容进行文字转录，并在最后添加<风格>标签，标签共8种：新闻科普、恐怖故事、童话故事、客服、诗歌散文、有声书、日常口语、其他。",
-    "SGC (Speaker Gender Classification)(类别:female,male)": "请将音频转录为文本，并在文本结尾处标注<性别>标签，性别为female或male。",
-    "SAP (Speaker Age Prediction)(类别:child、adult和old)": "请将音频转录为文本，并在文本结尾处标注<年龄>标签，年龄划分为child、adult和old三种。",
+    "VED (Vocal Event Detection)(Categories:laugh，cough，cry，screaming，sigh，throat clearing，sneeze，other)": "请将音频转录为文字记录，并在记录末尾标注<音频事件>标签，音频事件共8种：laugh，cough，cry，screaming，sigh，throat clearing，sneeze，other。",
+    "SER (Speech Emotion Recognition)(Categories:sad，anger，neutral，happy，surprise，fear，disgust，和other)": "请将音频内容转录成文字记录，并在记录末尾标注<情感>标签，情感共8种：sad，anger，neutral，happy，surprise，fear，disgust，和other。",
+    "SSR (Speaking Style Recognition)(Categories:新闻科普，恐怖故事，童话故事，客服，诗歌散文，有声书，日常口语，其他)": "请将音频内容进行文字转录，并在最后添加<风格>标签，标签共8种：新闻科普、恐怖故事、童话故事、客服、诗歌散文、有声书、日常口语、其他。",
+    "SGC (Speaker Gender Classification)(Categories:female,male)": "请将音频转录为文本，并在文本结尾处标注<性别>标签，性别为female或male。",
+    "SAP (Speaker Age Prediction)(Categories:child、adult和old)": "请将音频转录为文本，并在文本结尾处标注<年龄>标签，年龄划分为child、adult和old三种。",
     "STTC (Speech to Text Chat)": "首先将语音转录为文字，然后对语音内容进行回复，转录和文字之间使用<开始回答>分割。"
 }
 
@@ -171,29 +171,29 @@ with gr.Blocks(css=custom_css) as demo:
     # 添加音频输入和任务选择
     with gr.Row():
         with gr.Column(scale=1):
-            audio_input = gr.Audio(label="录音", type="filepath")
+            audio_input = gr.Audio(label="Record", type="filepath")
         with gr.Column(scale=1, min_width=300):  # 给输出框设置最小宽度，确保等高对齐
-            output_text = gr.Textbox(label="输出结果", lines=8, placeholder="生成的结果将显示在这里...", interactive=False)
+            output_text = gr.Textbox(label=" Output", lines=8, placeholder="The generated result will be displayed here...", interactive=False)
 
     # 添加任务选择和自定义输入框
     with gr.Row():
         task_dropdown = gr.Dropdown(
-            label="任务",
-            choices=list(TASK_PROMPT_MAPPING.keys()) + ["自主输入文本"],  # 新增选项
+            label="Task",
+            choices=list(TASK_PROMPT_MAPPING.keys()) + ["Custom Input Text"],  # 新增选项
             value="ASR (Automatic Speech Recognition)"
         )
-        custom_prompt_input = gr.Textbox(label="自定义任务提示", placeholder="请输入自定义任务提示...", visible=False)  # 新增文本输入框
+        custom_prompt_input = gr.Textbox(label="Custom Task Prompt", placeholder="Please enter a custom task prompt...", visible=False)  # 新增文本输入框
 
     # 添加按钮（下载按钮在左边，开始处理按钮在右边）
     with gr.Row():
-        download_button = gr.DownloadButton("下载音频", variant="secondary", elem_classes=["button-height", "download-button"])
-        submit_button = gr.Button("开始处理", variant="primary", elem_classes=["button-height", "submit-button"])
+        download_button = gr.DownloadButton("Download Recording", variant="secondary", elem_classes=["button-height", "download-button"])
+        submit_button = gr.Button("Start to Process", variant="primary", elem_classes=["button-height", "submit-button"])
 
     # 添加确认组件
     with gr.Row(visible=False) as confirmation_row:
-        gr.Markdown("请判断结果是否正确：")
+        gr.Markdown("Please determine whether the result is correct:")
         confirmation_buttons = gr.Radio(
-            choices=["正确", "错误"],
+            choices=["Correct", "Incorrect"],
             label="",
             interactive=True,
             container=False,