Update app.py

app.py

@@ -9,30 +9,30 @@ model = whisper.load_model("small")
 
 
 #option 1
-def transcribe(audio):
-    model = whisper.load_model("base")
-    result = model.transcribe(audio)
-    return result["text"]
-
-#option 2
 # def transcribe(audio):
+#     model = whisper.load_model("base")
+#     result = model.transcribe(audio)
+#     return result["text"]
+
+option 2
+def transcribe(audio):
     
-#     #time.sleep(3)
-#     # load audio and pad/trim it to fit 30 seconds
-#     audio = whisper.load_audio(audio)
-#     audio = whisper.pad_or_trim(audio)
-
-#     # make log-Mel spectrogram and move to the same device as the model
-#     mel = whisper.log_mel_spectrogram(audio).to(model.device)
-
-#     # detect the spoken language
-#     _, probs = model.detect_language(mel)
-#     print(f"Detected language: {max(probs, key=probs.get)}")
-
-#     # decode the audio
-#     options = whisper.DecodingOptions(fp16 = False)
-#     result = whisper.decode(model, mel, options)
-#     return result.text
+    #time.sleep(3)
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+
+    # decode the audio
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+    return result.text
     
     
 def process_text(input_text):
@@ -73,7 +73,7 @@ with gr.Blocks() as demo:
     
     b1 = gr.Button("Transcribe audio")
     b2 = gr.Button("<Placeholder for the prompted action>")
-    #b3 = gr.Button("Email report to your doctor")
+    # b3 = gr.Button("Email report to your doctor")
 
 
     text1 = gr.Textbox(lines=5)