from matplotlib.pyplot import text
import numpy as np
import soundfile as sf
import yaml

import tensorflow as tf

from tensorflow_tts.inference import TFAutoModel
from tensorflow_tts.inference import AutoProcessor
from tensorflow_tts.inference import AutoConfig
import gradio as gr

MODEL_NAMES = [
    "Fastspeech2 + Melgan", 
    "Tacotron2 + Melgan",
]

fastspeech = TFAutoModel.from_pretrained("tensorspeech/tts-fastspeech-ljspeech-en", name="fastspeech")
fastspeech2 = TFAutoModel.from_pretrained("tensorspeech/tts-fastspeech2-ljspeech-en", name="fastspeech2")
tacotron2 = TFAutoModel.from_pretrained("tensorspeech/tts-tacotron2-ljspeech-en", name="tacotron2")
melgan = TFAutoModel.from_pretrained("tensorspeech/tts-melgan-ljspeech-en", name="melgan")
mb_melgan = TFAutoModel.from_pretrained("tensorspeech/tts-mb_melgan-ljspeech-en", name="mb_melgan")
melgan_stft_config = AutoConfig.from_pretrained('TensorFlowTTS/examples/melgan_stft/conf/melgan_stft.v1.yaml')
melgan_stft = TFAutoModel.from_pretrained(
    config=melgan_stft_config,
    pretrained_path="melgan.stft-2M.h5",
    name="melgan_stft"
)

MODEL_DICT = {
    "Fastspeech2" : fastspeech2,
    "Tacotron2" : tacotron2,
    "Melgan": melgan,
    "MB-Melgan": mb_melgan,
    "Melgan-STFT": melgan_stft
}

def inference(input):
    input_text, model_type = input[0], input[1]

    text2mel_name, vocoder_name = model_type.split(" + ")
    text2mel_model, vocoder_model = MODEL_DICT[text2mel_name], MODEL_DICT[vocoder_name]
    processor = AutoProcessor.from_pretrained(text2mel_name)
    input_ids = processor.text_to_sequence(input_text)
    
    if text2mel_name == "Tacotron":
        _, mel_outputs, stop_token_prediction, alignment_history = text2mel_model.inference(
            tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
            tf.convert_to_tensor([len(input_ids)], tf.int32),
            tf.convert_to_tensor([0], dtype=tf.int32)
        )
    elif text2mel_name == "Fastspeech":
        mel_before, mel_outputs, duration_outputs = text2mel_model.inference(
            input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
            speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
            speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
        )
    elif text2mel_name == "Fastspeech2":
        mel_before, mel_outputs, duration_outputs, _, _ = text2mel_model.inference(
            tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
            speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
            speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
            f0_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
            energy_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
        )
    else:
        raise ValueError("Only TACOTRON, FASTSPEECH, FASTSPEECH2 are supported on text2mel_name")

    # vocoder part
    if vocoder_name == "Melgan" or vocoder_name == "Melgan-STFT":
        audio = vocoder_model(mel_outputs)[0, :, 0]
    elif vocoder_name == "MB-Melgan":
        audio = vocoder_model(mel_outputs)[0, :, 0]
    else:
        raise ValueError("Only MELGAN, MELGAN-STFT and MB_MELGAN are supported on vocoder_name")

    # if text2mel_name == "TACOTRON":
    #     return mel_outputs.numpy(), alignment_history.numpy(), audio.numpy()
    # else:
    #     return mel_outputs.numpy(), audio.numpy()

    sf.write('./audio_after.wav', audio, 22050, "PCM_16")
    return './audio_after.wav'
  
inputs = [
    gr.inputs.Textbox(lines=5, label="Input Text"),
    gr.inputs.Radio(label="Pick a TTS Model",choices=MODEL_NAMES,)
]

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


title = "Tensorflow TTS"
description = "Gradio demo for TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
article = "<p style='text-align: center'><a href='https://tensorspeech.github.io/TensorFlowTTS/'>TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2</a> | <a href='https://github.com/TensorSpeech/TensorFlowTTS'>Github Repo</a></p>"

examples = [
    ["TensorFlowTTS provides real-time state-of-the-art speech synthesis architectures such as Tacotron-2, Melgan, Multiband-Melgan, FastSpeech, FastSpeech2 based-on TensorFlow 2."],
    ["With Tensorflow 2, we can speed-up training/inference progress, optimizer further by using fake-quantize aware and pruning, make TTS models can be run faster than real-time and be able to deploy on mobile devices or embedded systems."]   
]

gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples).launch()