Update app.py

app.py

@@ -1,12 +1,8 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-import soundfile as sf
 from transformers import pipeline
-import torch
 from datasets import load_dataset
-
-# Initialize the client for the text generation model
-client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
+import soundfile as sf
+import torch
 
 # Initialize the TTS pipeline from Huggingface
 synthesizer = pipeline("text-to-speech", model="Futuresony/output")
@@ -15,61 +11,25 @@ synthesizer = pipeline("text-to-speech", model="Futuresony/output")
 embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
 speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    # Prepare the messages for the chatbot
-    messages = [{"role": "system", "content": system_message}]
-    
-    # Add history of previous conversation
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-    
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    # Generate the response from the model
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
-
+def text_to_speech(text):
     # Convert the generated text to speech
-    speech = synthesizer(response, forward_params={"speaker_embeddings": speaker_embedding})
+    speech = synthesizer(text, forward_params={"speaker_embeddings": speaker_embedding})
     
     # Save the generated speech to a file
-    sf.write("generated_speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
+    output_file = "generated_speech.wav"
+    sf.write(output_file, speech["audio"], samplerate=speech["sampling_rate"])
     
-    # Return both the text and the audio for playback
-    return response, "generated_speech.wav"
+    # Return the path to the audio file for playback
+    return output_file
 
-# Create the Gradio interface with a textbox for the user to input a message
+# Create the Gradio interface
 demo = gr.Interface(
-    fn=respond,
-    inputs=[
-        gr.Textbox(label="Type your message here", placeholder="Enter message...", lines=2),
-        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)"),
-    ],
-    outputs=[gr.Textbox(label="Generated Response"), gr.Audio(label="Generated Speech")],
+    fn=text_to_speech,
+    inputs=gr.Textbox(label="Enter Text", placeholder="Type something..."),
+    outputs=gr.Audio(label="Generated Speech"),
+    title="Text-to-Speech Generator",
+    description="Enter text and generate speech using a pre-trained TTS model."
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo