Update app.py

app.py

@@ -20,25 +20,37 @@ def transcribe(audio):
     mel = whisper.log_mel_spectrogram(audio).to(model.device)
     
 
-    # detect the spoken language
-    # mel = mel.to("float32")  # もしくは mel = mel.to("float32")
+    # detect the spoken language    
     _, probs = model.detect_language(mel)
         
     print(f"Detected language: {max(probs, key=probs.get)}")
     detect_lang = max(probs, key=probs.get)
 
+    
+
     # decode the audio
     # options = whisper.DecodingOptions()
     options = whisper.DecodingOptions(fp16 = False)
     result = whisper.decode(model, mel, options)
 
-
+    if detect_lang == "en":
+      print("Text: ", result.text)
+      translated_text = translate(result.text, "JA")
+      print("translated_text: ", translated_text)
+      # generated_video = text_to_speech(translated_text)
+      # print("generated_video 01: ", generated_video)
+    elif detect_lang == "ja":
+      print("Text: ", result.text)
+      translated_text = translate(result.text, "EN-US")
+        
     translated_text = translate(result.text, "JA")
     return translated_text
 
+
+    
 import gradio as gr
 
-title = 'Video to Translator'
+title = 'Translator_Video'
 
 inputs = gr.Video()
 outputs = gr.Text()