Update app.py

app.py

@@ -3,7 +3,7 @@ from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from datasets import load_dataset
 import spacy
 import gradio as gr
-import numpy as np  # 確保導入 Numpy
+from pydub import AudioSegment  # 引入 pydub 庫
 
 # 設置設備和環境變數（如有需要）
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
@@ -36,9 +36,19 @@ except Exception as e:
 
 def process_audio(audio_file):
     
+        # 將 MP3 轉換為 WAV
+    
+        try:
+            audio_segment = AudioSegment.from_mp3(audio_file)
+            wav_path = audio_file.replace(".mp3", ".wav")
+            audio_segment.export(wav_path, format="wav")
+            
+        except Exception as e:
+            print(f"MP3 轉 WAV 時出現錯誤：{e}")
+        
         # 語音轉文字
             
-        result= whisper_pipe(audio_file)["text"]
+        result= whisper_pipe(wav_path)["text"]
                 
         # 使用 T5 作為替代模型