restore old app

app.py

@@ -8,35 +8,44 @@ import firebase_admin
 from firebase_admin import credentials, firestore, storage
 from datetime import datetime, timedelta
 import json
-tmpdir = None
+import tempfile
+import uuid
 
-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"處理文件錯誤: {e}"
-
-# Initialize Firebase
+# LOCAL INITIALIZATION - ONLY USE ON YOUR OWN DEVICE 
+'''
+os.chdir(os.path.dirname(os.path.abspath(__file__)))
+cred = credentials.Certificate("serviceAccountKey.json")
+'''
+# Deployed Initialization
 firebase_config = json.loads(os.environ.get('firebase_creds'))
 cred = credentials.Certificate(firebase_config)
+
 firebase_admin.initialize_app(cred, {
     "storageBucket": "amis-asr-corrections-dem-8cf3d.firebasestorage.app"
 })
 db = firestore.client()
 bucket = storage.bucket()
 
-# Load ASR model and processor
+# Load the ASR model and processor
 MODEL_NAME = "eleferrand/XLSR_paiwan"
 processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME)
 model = AutoModelForCTC.from_pretrained(MODEL_NAME)
 
+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"處理文件錯誤: {e}"
+
 def transcribe_both(audio_file):
+    start_time = datetime.now()
     transcription = transcribe(audio_file)
     return transcription, transcription
 
@@ -44,103 +53,155 @@ def store_correction(original_transcription, corrected_transcription, audio_file
     try:
         audio_metadata = {}
         audio_file_url = None
+        
+        # If an audio file is provided, upload it to Firebase Storage
         if audio_file and os.path.exists(audio_file):
             audio, sr = librosa.load(audio_file, sr=44100)
             duration = librosa.get_duration(y=audio, sr=sr)
             file_size = os.path.getsize(audio_file)
             audio_metadata = {'duration': duration, 'file_size': file_size}
+            
+            # Generate a unique identifier for the audio file
             unique_id = str(uuid.uuid4())
             destination_path = f"audio/pai/{unique_id}.wav"
+            
+            # Create a blob and upload the file
             blob = bucket.blob(destination_path)
             blob.upload_from_filename(audio_file)
+            
+            # Generate a signed download URL valid for 1 hour (adjust expiration as needed)
             audio_file_url = blob.generate_signed_url(expiration=timedelta(hours=1))
+        
         combined_data = {
-            'transcription_info': {'original_text': original_transcription, 'corrected_text': corrected_transcription, 'language': 'pai'},
-            'audio_data': {'audio_metadata': audio_metadata, 'audio_file_url': audio_file_url},
-            'user_info': {'native_paiwan_speaker': native_speaker, 'age': age},
-            'timestamp': datetime.now().isoformat(), 'model_name': MODEL_NAME
+            'transcription_info': {
+                'original_text': original_transcription,
+                'corrected_text': corrected_transcription,
+                'language': 'pai',
+            },
+            'audio_data': {
+                'audio_metadata': audio_metadata,
+                'audio_file_url': audio_file_url,
+            },
+            'user_info': {
+                'native_paiwan_speaker': native_speaker,
+                'age': age
+            },
+            'timestamp': datetime.now().isoformat(),
+            'model_name': MODEL_NAME
         }
+        # Save data to a collection for that language 
         db.collection('paiwan_transcriptions').add(combined_data)
-        return "校正保存成功!"
+        return "校正保存成功! (Correction saved successfully!)"
     except Exception as e:
-        return f"保存失败: {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=orig_txt)
+        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)
-        zf.write(corr_txt, arcname=corr_txt)
+        zf.write(corr_txt, arcname="corrected_transcription.txt")
         os.remove(corr_txt)
     return tmp_zip.name
 
+def toggle_language(switch):
+    """Switch UI text between English and Traditional Chinese"""
+    if switch:
+        return (
+            "排灣語自動語音識別逐字稿與修正系統", 
+            "步驟 1：音訊上傳與逐字稿",
+            "步驟 2：審閱與編輯逐字稿",
+            "步驟 3：使用者資訊",
+            "步驟 4：儲存與下載",
+            "音訊輸入", "語音辨識",
+            "原始逐字稿", "更正逐字稿",
+            "年齡", "母語排灣語使用者?",
+            "儲存更正", "儲存狀態",
+            "下載 ZIP 檔案"
+        )
+    else:
+        return (
+            "Paiwan ASR Transcription & Correction System", 
+            "Step 1: Audio Upload & Transcription",
+            "Step 2: Review & Edit Transcription",
+            "Step 3: User Information",
+            "Step 4: Save & Download",
+            "Audio Input", "Transcribe Audio",
+            "Original Transcription", "Corrected Transcription",
+            "Age", "Native Paiwan Speaker?",
+            "Save Correction", "Save Status",
+            "Download ZIP File"
+        )
+
 # Interface
 with gr.Blocks() as demo:
-    title = gr.Markdown("排灣語自動語音識別校正系統 (Paiwan ASR Transcription & Correction System)")
-    step1 = gr.Markdown(
-        "步驟 1：音訊上傳與產生逐字稿 (Audio Upload & Automatic Transcription)\n\n上傳後系統將自動產生逐字稿，請耐心等待。"
-    )
+    lang_switch = gr.Checkbox(label="切換到繁體中文 (Switch to Traditional Chinese)")
+    
+    title = gr.Markdown("Paiwan ASR Transcription & Correction System")
+    step1 = gr.Markdown("Step 1: Audio Upload & Transcription")
+    
     with gr.Row():
-        audio_input = gr.Audio(
-            sources=["upload", "microphone"], type="filepath", label="音訊輸入 (Audio Input)"
-        )
-
-    step2 = gr.Markdown("步驟 2：審閱與編輯逐字稿 (Step 2: Review & Edit Transcription)")
+        audio_input = gr.Audio(sources=["upload", "microphone"], type="filepath", label="Audio Input")
+    
+    step2 = gr.Markdown("Step 2: Review & Edit Transcription")
     with gr.Row():
-        original_text = gr.Textbox(
-            label="原始逐字稿 (Original Transcription)", interactive=False, lines=5
-        )
-        corrected_text = gr.Textbox(
-            label="更正逐字稿 (Corrected Transcription)", interactive=True, lines=5
-        )
-    # Automatically generate transcription on audio upload
-    audio_input.change(
-        transcribe_both,
-        inputs=audio_input,
-        outputs=[original_text, corrected_text],
-        queue=True
-    )
+        transcribe_button = gr.Button("Transcribe Audio")
+    
+    original_text = gr.Textbox(label="Original Transcription", interactive=False, lines=5)
+    corrected_text = gr.Textbox(label="Corrected Transcription", interactive=True, lines=5)
 
-    step3 = gr.Markdown("步驟 3：使用者資訊 (Step 3: User Information)")
+    step3 = gr.Markdown("Step 3: User Information")
     with gr.Row():
-        age_input = gr.Slider(
-            minimum=0, maximum=100, step=1, label="年齡 (Age)", value=25
-        )
-        native_speaker_input = gr.Checkbox(
-            label="母語排灣語使用者? (Native Paiwan Speaker?)", value=True
-        )
+        age_input = gr.Slider(minimum=0, maximum=100, step=1, label="Age", value=25)
+        native_speaker_input = gr.Checkbox(label="Native Paiwan Speaker?", value=True)
 
-    step4 = gr.Markdown("步驟 4：儲存與下載 (Step 4: Save & Download)")
+    step4 = gr.Markdown("Step 4: Save & Download")
     with gr.Row():
-        save_button = gr.Button("儲存 (Save)")
-        save_status = gr.Textbox(
-            label="儲存狀態 (Save Status)", interactive=False
-        )
-
+        save_button = gr.Button("Save Correction")
+        save_status = gr.Textbox(label="Save Status", interactive=False)
+    
     with gr.Row():
-        download_button = gr.Button("下載 ZIP 檔案 (Download ZIP File)")
+        download_button = gr.Button("Download ZIP File")
         download_output = gr.File()
 
+    lang_switch.change(
+        toggle_language, 
+        inputs=lang_switch, 
+        outputs=[title, step1, step2, step3, step4, audio_input, transcribe_button,
+                 original_text, corrected_text, age_input, native_speaker_input,
+                 save_button, save_status, download_button]
+    )
+
+    transcribe_button.click(
+        transcribe_both, 
+        inputs=audio_input, 
+        outputs=[original_text, corrected_text]
+    )
+
     save_button.click(
-        store_correction,
-        inputs=[original_text, corrected_text, audio_input, age_input, native_speaker_input],
+        store_correction, 
+        inputs=[original_text, corrected_text, audio_input, age_input, native_speaker_input], 
         outputs=save_status
     )
+
     download_button.click(
-        prepare_download,
-        inputs=[audio_input, original_text, corrected_text],
+        prepare_download, 
+        inputs=[audio_input, original_text, corrected_text], 
         outputs=download_output
     )
 
-demo.launch()
+demo.launch()