fix chinese

app.py

@@ -12,7 +12,7 @@ import tempfile
 
 # Initialize Firebase
 firebase_config = json.loads(os.environ.get('firebase_creds'))
-cred = credentials.Certificate(firebase_config)
+cred = credentials.Certificate(firebase_config)  # Your Firebase JSON key file
 firebase_admin.initialize_app(cred)
 db = firestore.client()
 
@@ -21,61 +21,18 @@ MODEL_NAME = "eleferrand/xlsr53_Amis"
 processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME)
 model = AutoModelForCTC.from_pretrained(MODEL_NAME)
 
-# Language configuration
-LANGUAGE = {
-    "en": {
-        "title": "ASR Demo with Editable Transcription",
-        "step1": "Step 1: Audio Upload & Transcription",
-        "audio_input": "Audio Input",
-        "transcribe_btn": "Transcribe Audio",
-        "step2": "Step 2: Review & Edit Transcription",
-        "original_text": "Original Transcription",
-        "corrected_text": "Corrected Transcription",
-        "transcription_placeholder": "Transcription will appear here...",
-        "step3": "Step 3: User Information",
-        "age_label": "Age",
-        "native_speaker": "Native Amis Speaker",
-        "step4": "Step 4: Save & Download",
-        "save_btn": "Save Correction to Database",
-        "save_status": "Save Status",
-        "download_btn": "Download Results (ZIP)",
-        "status_placeholder": "Status messages will appear here...",
-        "toggle_lang": "中文/English"
-    },
-    "zh": {
-        "title": "可編輯轉寫的語音辨識演示",
-        "step1": "步驟一: 音頻上傳與轉寫",
-        "audio_input": "音頻輸入",
-        "transcribe_btn": "開始轉寫",
-        "step2": "步驟二: 校對與編輯轉寫結果",
-        "original_text": "原始轉寫結果",
-        "corrected_text": "校正後文本",
-        "transcription_placeholder": "轉寫結果將顯示在此處...",
-        "step3": "步驟三: 用戶資訊",
-        "age_label": "年齡",
-        "native_speaker": "阿美族母語者",
-        "step4": "步驟四: 保存與下載",
-        "save_btn": "保存校正結果至數據庫",
-        "save_status": "保存狀態",
-        "download_btn": "下載結果(ZIP壓縮檔)",
-        "status_placeholder": "狀態訊息將顯示在此處...",
-        "toggle_lang": "English/中文"
-    }
-}
-
-current_lang = gr.State(value="en")
-
 def transcribe(audio_file):
     try:
         audio, rate = librosa.load(audio_file, sr=16000)
         input_values = processor(audio, sampling_rate=16000, return_tensors="pt").input_values
+
         with torch.no_grad():
             logits = model(input_values).logits
         predicted_ids = torch.argmax(logits, dim=-1)
         transcription = processor.batch_decode(predicted_ids)[0]
         return transcription.replace("[UNK]", "")
     except Exception as e:
-        return f"Error processing file: {e}"
+        return f"处理文件错误: {e}"
 
 def transcribe_both(audio_file):
     start_time = datetime.now()
@@ -105,23 +62,26 @@ def store_correction(original_transcription, corrected_transcription, audio_file
             }
         }
         db.collection('transcriptions').add(combined_data)
-        return "Correction saved successfully!"
+        return "校正保存成功! (Correction saved successfully!)"
     except Exception as e:
-        return f"Error saving correction: {e}"
+        return f"保存失败: {e} (Error saving correction: {e})"
 
 def prepare_download(audio_file, original_transcription, corrected_transcription):
     if audio_file is None:
         return None
+
     tmp_zip = tempfile.NamedTemporaryFile(delete=False, suffix=".zip")
     tmp_zip.close()
     with zipfile.ZipFile(tmp_zip.name, "w") as zf:
         if os.path.exists(audio_file):
             zf.write(audio_file, arcname="audio.wav")
+        
         orig_txt = "original_transcription.txt"
         with open(orig_txt, "w", encoding="utf-8") as f:
             f.write(original_transcription)
         zf.write(orig_txt, arcname="original_transcription.txt")
         os.remove(orig_txt)
+
         corr_txt = "corrected_transcription.txt"
         with open(corr_txt, "w", encoding="utf-8") as f:
             f.write(corrected_transcription)
@@ -129,117 +89,116 @@ def prepare_download(audio_file, original_transcription, corrected_transcription
         os.remove(corr_txt)
     return tmp_zip.name
 
-def toggle_language(lang):
-    new_lang = "zh" if lang == "en" else "en"
-    lang_dict = LANGUAGE[new_lang]
-    return [
-        gr.Markdown.update(value=f"<h1 class='header'>{lang_dict['title']}</h1>"),
-        gr.Markdown.update(value=f"### {lang_dict['step1']}"),
-        gr.Audio.update(label=lang_dict['audio_input']),
-        gr.Button.update(value=lang_dict['transcribe_btn']),
-        gr.Markdown.update(value=f"### {lang_dict['step2']}"),
-        gr.Textbox.update(label=lang_dict['original_text'], placeholder=lang_dict['transcription_placeholder']),
-        gr.Textbox.update(label=lang_dict['corrected_text'], placeholder=lang_dict['transcription_placeholder']),
-        gr.Markdown.update(value=f"### {lang_dict['step3']}"),
-        gr.Slider.update(label=lang_dict['age_label']),
-        gr.Checkbox.update(label=lang_dict['native_speaker']),
-        gr.Markdown.update(value=f"### {lang_dict['step4']}"),
-        gr.Button.update(value=lang_dict['save_btn']),
-        gr.Textbox.update(label=lang_dict['save_status'], placeholder=lang_dict['status_placeholder']),
-        gr.Button.update(value=lang_dict['download_btn']),
-        gr.File.update(label=lang_dict['download_btn']),
-        gr.Button.update(value=lang_dict['toggle_lang']),
-        new_lang
-    ]
-
+# 界面设计
 with gr.Blocks(css="""
-    .container { max-width: 800px; margin: auto; padding: 20px; font-family: Arial, sans-serif; }
-    .header { text-align: center; margin-bottom: 30px; }
-    .section { margin-bottom: 30px; padding: 15px; border: 1px solid #ddd; border-radius: 8px; background-color: #f9f9f9; }
-    .section h3 { margin-top: 0; margin-bottom: 15px; text-align: center; }
-    .button-row { display: flex; justify-content: center; gap: 10px; flex-wrap: wrap; }
-    .lang-toggle { position: absolute; top: 20px; right: 20px; }
-    @media (max-width: 600px) { .gradio-row { flex-direction: column; } }
+    .container { 
+        max-width: 800px; 
+        margin: auto; 
+        padding: 20px; 
+        font-family: Arial, sans-serif;
+    }
+    .header { 
+        text-align: center; 
+        margin-bottom: 30px; 
+    }
+    .section { 
+        margin-bottom: 30px; 
+        padding: 15px; 
+        border: 1px solid #ddd; 
+        border-radius: 8px; 
+        background-color: #f9f9f9;
+    }
+    .section h3 {
+        margin-top: 0;
+        margin-bottom: 15px;
+        text-align: center;
+    }
+    .button-row {
+        display: flex;
+        justify-content: center;
+        gap: 10px;
+        flex-wrap: wrap;
+    }
+    @media (max-width: 600px) {
+      .gradio-row { 
+          flex-direction: column; 
+      }
+    }
 """) as demo:
-    current_lang.render()
-    
     with gr.Column(elem_classes="container"):
-        with gr.Row():
-            title_md = gr.Markdown(elem_classes="header")
-            lang_btn = gr.Button(LANGUAGE['en']['toggle_lang'], elem_classes="lang-toggle")
+        gr.Markdown("<h1 class='header'>阿美語轉錄與修正系統 (ASR Correction System)</h1>")
         
-        # Step 1
         with gr.Column(elem_classes="section"):
-            step1_md = gr.Markdown()
+            gr.Markdown("### 步驟 1：音訊上傳與轉錄(Audio Upload & Transcription)")
             with gr.Row():
-                audio_input = gr.Audio(sources=["upload", "microphone"], type="filepath")
-                transcribe_button = gr.Button(variant="primary")
+                audio_input = gr.Audio(
+                    sources=["upload", "microphone"],
+                    type="filepath",
+                    label="音訊輸入 (Audio Input)"
+                )
+                transcribe_button = gr.Button("轉錄音訊 (Transcribe Audio)", variant="primary")
             proc_time_state = gr.State()
         
-        # Step 2
         with gr.Column(elem_classes="section"):
-            step2_md = gr.Markdown()
+            gr.Markdown("### 步驟 2：審閱與編輯轉錄 (Review & Edit Transcription)")
             with gr.Row():
-                original_text = gr.Textbox(interactive=False, lines=5)
-                corrected_text = gr.Textbox(interactive=True, lines=5)
+                original_text = gr.Textbox(
+                    label="原始轉錄 (Original Transcription)",
+                    interactive=False,
+                    lines=5,
+                    placeholder="謄本將在此出現... (Transcription will appear here...)"
+                )
+                corrected_text = gr.Textbox(
+                    label="更正轉錄 (Corrected Transcription)",
+                    interactive=True,
+                    lines=5,
+                    placeholder="在此編輯轉錄... (Edit transcription here...)"
+                )
         
-        # Step 3
         with gr.Column(elem_classes="section"):
-            step3_md = gr.Markdown()
+            gr.Markdown("### 步驟 3：使用者資訊 (User Information)")
             with gr.Row():
-                age_input = gr.Slider(minimum=0, maximum=100, step=1, value=25)
-                native_speaker_input = gr.Checkbox(value=True)
+                age_input = gr.Slider(
+                    minimum=0,
+                    maximum=100,
+                    step=1,
+                    label="年齡 (Age)",
+                    value=25
+                )
+                native_speaker_input = gr.Checkbox(
+                    label="以阿美語為母語？ (Native Amis Speaker?)",
+                    value=True
+                )
         
-        # Step 4
         with gr.Column(elem_classes="section"):
-            step4_md = gr.Markdown()
+            gr.Markdown("### 步驟 4：儲存與下載 (Save & Download)")
             with gr.Row(elem_classes="button-row"):
-                save_button = gr.Button(variant="primary")
-                save_status = gr.Textbox(interactive=False)
+                save_button = gr.Button("儲存更正 (Save Correction)", variant="primary")
+                save_status = gr.Textbox(
+                    label="儲存狀態 (Save Status)",
+                    interactive=False,
+                    placeholder="狀態訊息會出現在這裡... (Status messages will appear here...)"
+                )
             with gr.Row(elem_classes="button-row"):
-                download_button = gr.Button()
-                download_output = gr.File()
-    
-    lang_btn.click(
-        toggle_language,
-        inputs=current_lang,
-        outputs=[
-            title_md, step1_md, audio_input, transcribe_button,
-            step2_md, original_text, corrected_text, step3_md,
-            age_input, native_speaker_input, step4_md, save_button,
-            save_status, download_button, download_output, lang_btn,
-            current_lang
-        ]
-    )
-    
-    transcribe_button.click(
-        transcribe_both,
-        inputs=audio_input,
-        outputs=[original_text, corrected_text, proc_time_state]
-    )
-    
-    save_button.click(
-        store_correction,
-        inputs=[original_text, corrected_text, audio_input, proc_time_state, age_input, native_speaker_input],
-        outputs=save_status
-    )
-    
-    download_button.click(
-        prepare_download,
-        inputs=[audio_input, original_text, corrected_text],
-        outputs=download_output
-    )
-    
-    demo.load(
-        toggle_language,
-        inputs=current_lang,
-        outputs=[
-            title_md, step1_md, audio_input, transcribe_button,
-            step2_md, original_text, corrected_text, step3_md,
-            age_input, native_speaker_input, step4_md, save_button,
-            save_status, download_button, download_output, lang_btn,
-            current_lang
-        ]
-    )
+                download_button = gr.Button("下載 ZIP 檔案 (Download ZIP)")
+                download_output = gr.File(label="下載 ZIP 檔案  (Download ZIP)")
+
+        transcribe_button.click(
+            fn=transcribe_both,
+            inputs=audio_input,
+            outputs=[original_text, corrected_text, proc_time_state]
+        )
+        
+        save_button.click(
+            fn=store_correction,
+            inputs=[original_text, corrected_text, audio_input, proc_time_state, age_input, native_speaker_input],
+            outputs=save_status
+        )
+        
+        download_button.click(
+            fn=prepare_download,
+            inputs=[audio_input, original_text, corrected_text],
+            outputs=download_output
+        )
 
 demo.launch(share=True)