from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub
from fairseq.models.text_to_speech.hub_interface import TTSHubInterface
import IPython.display as ipd
import gradio as gr
import soundfile as sf

models, cfg, task = load_model_ensemble_and_task_from_hf_hub(
    "facebook/tts_transformer-tr-cv7",
    arg_overrides={"vocoder": "hifigan", "fp16": False}
)
model = models[0]
TTSHubInterface.update_cfg_with_data_cfg(cfg, task.data_cfg)
generator = task.build_generator([model], cfg)

def tts(text):
  sample = TTSHubInterface.get_model_input(task, text)
  wav, rate = TTSHubInterface.get_prediction(task, model, generator, sample)
  sf.write('./audio_after.wav', wav, rate, "PCM_16")
  return './audio_after.wav'

outputs = gr.Audio(type="filepath", label="Output Audio")

demo = gr.Interface(fn=tts, inputs=gr.inputs.Textbox(placeholder="Lütfen Cümle Giriniz...", lines=5), outputs=outputs)

demo.launch()