Update app.py

app.py

@@ -1,11 +1,14 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import soundfile as sf
+import torch
+from transformers import pipeline
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
+# Set up your TTS model (as before)
+synthesiser = pipeline("text-to-speech", "Futuresony/output")
 
+# Set up your text generation client
+client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
 def respond(
     message,
@@ -15,6 +18,7 @@ def respond(
     temperature,
     top_p,
 ):
+    # Generate text response from your model
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -26,7 +30,6 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,30 +38,34 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
+    # Convert the generated text into speech (Text-to-Speech)
+    # Get speaker embedding (optional, if you want to control the speaker)
+    embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+    speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+
+    # Generate speech from the text response
+    speech = synthesiser(response, forward_params={"speaker_embeddings": speaker_embedding})
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    # Save the speech to a file (you can play it on the fly or return it in other formats like MP3)
+    sf.write("generated_speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
+
+    return response, "generated_speech.wav"
+    # You can return the text along with speech if needed
+
+
+# Create the Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()