Update app.py

app.py

@@ -1,29 +1,26 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from IPython.display import Audio
+from transformers import pipeline
 
-# Load the model and tokenizer
-model_name = "facebook/wav2vec2-large-xlsr-53"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+pipe = pipeline("text-to-speech", model="suno/bark-small")
 
-# Define the Gradio interface
 def text_to_speech(text):
-    # Tokenize the input text
-    inputs = tokenizer(text, return_tensors="pt", padding=True)
+    output = pipe(text)
+    audio = Audio(output[0]["audio"], rate=output[0]["sampling_rate"])
+    return audio
 
-    # Generate speech from the input text using the loaded model
-    with torch.no_grad():
-        outputs = model.generate(**inputs)
-    
-    # Convert the generated speech tensor to audio format
-    speech = gradio.inputs.Audio(outputs[0].numpy().tolist(), type='torch')
+iface = gr.Interface(
+    fn=text_to_speech,
+    inputs="text",
+    outputs="audio",
+    title="Text-to-Speech",
+    description="Convert text to speech using Hugging Face's TTS model",
+    examples=[
+        ["Hello, how are you?"],
+        ["Could you please repeat that?"],
+        ["This is a test."],
+    ],
+    article="https://huggingface.co/models",
+)
 
-    return speech
-
-# Create the Gradio interface
-iface = gr.Interface(fn=text_to_speech, inputs="text", outputs="audio", 
-                     title="Text-to-Speech App", 
-                     description="Enter text to hear the speech")
-
-# Launch the Gradio interface
-iface.launch()
+iface.launch()