Update app.py

app.py

@@ -21,12 +21,12 @@ def guessanAge(model, image):
         description = imgclassifier(image)
     return description    
 
-def text2speech(model, text):
+def text2speech(model, text, voice):
     if len(text) > 0:
         synthesiser = pipeline("text-to-speech", model=model)
         
         embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
-        speaker_embedding = torch.tensor(embeddings_dataset[4535]["xvector"]).unsqueeze(0)
+        speaker_embedding = torch.tensor(embeddings_dataset[voice]["xvector"]).unsqueeze(0)
         
         speech = synthesiser(text, forward_params={"speaker_embeddings": speaker_embedding})
         audio_data = np.frombuffer(speech["audio"], dtype=np.float32)
@@ -49,9 +49,10 @@ tab2 = gr.Interface(
 )
 
 radio3 = gr.Radio(["microsoft/speecht5_tts"], label="Select an tts", info="Age Classifier")
+radio3_1 = gr.Radio([("Scottish male", 0), ("US male", 1138), ("US female", 2271), ("Canadian male",3403), ("Indian male", 4535), ("US male", 5667), (6799, "US female")])
 tab3 = gr.Interface(
     fn=text2speech,
-    inputs=[radio3, "text"],
+    inputs=[radio3, "text", radio3_1],
     outputs=["audio"],
 )