Update app.py

app.py

@@ -2,17 +2,15 @@ import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from datasets import load_dataset
 import spacy
-import gradio as gr
 
-# 設置設備
+# 設置設備和環境變數（如有需要）
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
 # Whisper 模型初始化（語音轉文字）
 whisper_model_id = "openai/whisper-large-v3"
 whisper_model = AutoModelForSpeechSeq2Seq.from_pretrained(
-    whisper_model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
-)
+    whisper_model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True)
 whisper_model.to(device)
 whisper_processor = AutoProcessor.from_pretrained(whisper_model_id)
 
@@ -21,48 +19,60 @@ whisper_pipe = pipeline(
     model=whisper_model,
     tokenizer=whisper_processor.tokenizer,
     feature_extractor=whisper_processor.feature_extractor,
-    device=device,
-)
-
-# DeepSeek-V3 模型初始化（文本生成）
-deepseek_pipe = None  # 預設值，以防模型加載失敗
+    device=device)
 
+# 安裝必要庫並下載 spaCy 英文小模型（如果尚未安裝）
 try:
-    deepseek_pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3", trust_remote_code=True)
+    
 except Exception as e:
-    print(f"加載模型時出現錯誤：{e}")
+    
+finally:
+    
+spacy.cli.download("en_core_web_sm")
 
-# spaCy 初始化（文本分類與標籤）
 nlp = spacy.load("en_core_web_sm")
 
 def process_audio(audio_file):
     
-        # 語音轉文字
-        result = whisper_pipe(audio_file)["text"]
         
-        # 使用 DeepSeek 生成回應（如果成功加載模型）
-        if deepseek_pipe is not None:  
-            messages=[{"role": "user", "content": result}]
-            deepseek_response=deepseek_pipe(messages)[0]["generated_text"]
+            
+            # 語音轉文字
+            
+            result= whisper_pipe(audio_file)["text"]
+            
+                
+                # 使用其他文本生成模型替換，因為目前無法直接加載DeepSeek-V3
                 
-            doc=nlp(deepseek_response)
-            entities=[(ent.text, ent.label_) for ent in doc.ents]
+                messages=[{"role": "user", "content": result}]
                 
-            return {
-                "Transcription (Whisper)": result,
-                "AI Response (DeepSeek)": deepseek_response,
-                "Extracted Entities (spaCy)": entities
+                deepseek_response="" # 預設回應
+                
+                try: 
+                    from transformers import pipeline
                     
+                    pipe=pipeline("text-generation",model="t5-base")
                     
+                    deepseek_response=pipe(messages)[0]["generated_text"]
                     
-                    }
+                        
+                        
+                        # 使用 spaCy 分析文本
+                        
+                        doc=nlp(deepseek_response)
+                        entities=[(ent.text, ent.label_) for ent in doc.ents]
+                        
+                        return {
+                            "Transcription (Whisper)": result,
+                            "AI Response (T5)": deepseek_response,# 修改為 T5 回應以避免與原來不同步                            
+                            "Extracted Entities (spaCy)": entities}
                     
-        else:
-            return {
-                "Transcription (Whisper)": result,
-                # 可以添加預設回應或錯誤信息
-                
-                    }
+                except Exception as e: 
+                    return {
+                        "Transcription (Whisper)": result,# 保留原始轉錄內容
+                        
+                        }
+                    
+
 
 with gr.Blocks() as app: