Create app.py

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+from transformers import AutoProcessor, AutoModelForTextToSpectrogram
+from datasets import load_dataset
+import torch
+import soundfile as sf
+import os
+
+# Load models and processors
+processor = AutoProcessor.from_pretrained("ayush2607/speecht5_tts_technical_data")
+model = AutoModelForTextToSpectrogram.from_pretrained("ayush2607/speecht5_tts_technical_data")
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+
+# Load xvector containing speaker's voice characteristics from a dataset
+embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+
+def text_to_speech(text):
+    inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
+    
+    output_path = "output.wav"
+    sf.write(output_path, speech.numpy(), samplerate=16000)
+    
+    return output_path
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=text_to_speech,
+    inputs=gr.Textbox(label="Enter text to convert to speech"),
+    outputs=gr.Audio(label="Generated Speech"),
+    title="Text-to-Speech Converter",
+    description="Convert text to speech using the SpeechT5 model."
+)
+
+# Launch the app
+iface.launch()