from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech
import numpy as np

tts_model = SpeechT5ForTextToSpeech.from_pretrained("ThuraAung1601/speecht5_for_thai_with_ipa_tts_v1")

ipa_processor = SpeechT5Processor.from_pretrained("ThuraAung1601/speecht5_for_thai_with_ipa_tts_v1")
ipa_tokenizer = ipa_processor.tokenizer
ipa_tokenizer.decode(ipa_tokenizer(text)["input_ids"])

loaded_np = np.load("speaker_embedding_304.npy")
speaker_embedding = torch.tensor(loaded_np)

text = "ที่ข้าพเจ้าได้เคยล่วงเกินท่านไว้"

from pythainlp.tokenize import word_tokenize
from pythainlp.transliterate import transliterate

def thai2ipa_dict(text):
    result = []
    for word in word_tokenize(text):
        result.append(transliterate(word).replace(" ", ""))
    return "".join(result)

ipa = thai2ipa_dict(text)

model_input = ipa_processor(text=ipa, return_tensors="pt")

spectrogram = tts_model.generate_speech(model_input["input_ids"], speaker_embedding)

from transformers import SpeechT5HifiGan
the_vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")

with torch.no_grad():
    speech = the_vocoder(spectrogram)

import soundfile as sf
sf.write("output.wav", speech.numpy(), samplerate=16000)