from transformers import pipeline
from datasets import load_dataset
import soundfile as sf
import torch
import gradio as gr

# Text-to-speech pipeline
synthesiser = pipeline("text-to-speech", "microsoft/speecht5_tts")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")

def synthesize_speech(text, speaker_id):
    speaker_embedding = torch.tensor(embeddings_dataset[speaker_id]["xvector"]).unsqueeze(0)
    speech = synthesiser(text, forward_params={"speaker_embeddings": speaker_embedding})
    sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
    return "speech.wav"

# Define your interface
iface = gr.Interface(
    fn=synthesize_speech,
    inputs=[gr.Textbox(label="Enter your text"), gr.Slider(minimum=0, maximum=len(embeddings_dataset)-1, label="Speaker ID")],
    outputs="audio",
    title="Text-to-Speech Synthesizer",
    description="Type a text and choose a speaker to synthesize speech."
)

# Launch the app
iface.launch()