Update app.py

app.py

@@ -21,6 +21,14 @@ def guessanAge(model, image):
         description = imgclassifier(image)
     return description    
 
+def text2speech(model, text):
+    st.write("using model:"+model)
+    if len(text) > 0:
+        speechclassifier  = pipeline("text-to-speech", model=model)
+        embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+        speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+        output = speechclassifier(text, forward_params={"speaker_embeddings": speaker_embedding})
+        return output
 
 radio1 = gr.Radio(["microsoft/resnet-50", "google/vit-base-patch16-224", "apple/mobilevit-small"], label="Select a Classifier", info="Image Classifier")
 tab1 = gr.Interface(
@@ -36,5 +44,12 @@ tab2 = gr.Interface(
     outputs=["text"],
 )
 
-demo = gr.TabbedInterface([tab1, tab2], ["tab1", "tab2"])
+radio3 = gr.Radio(["microsoft/speecht5_tts"], label="Select an tts", info="Age Classifier")
+tab3 = gr.Interface(
+    fn=text2speech,
+    inputs=[radio3, "text"],
+    outputs=["audio"],
+)
+
+demo = gr.TabbedInterface([tab1, tab2, tab3], ["tab1", "tab2", "tab3"])
 demo.launch()