bert_vits2/text/japanese_bert_v111.py

import torch

from contants import config


def get_bert_feature(text, word2ph, tokenizer, model, device=config.system.device, **kwargs):
    with torch.no_grad():
        inputs = tokenizer(text, return_tensors="pt")
        for i in inputs:
            inputs[i] = inputs[i].to(device)
        res = model(**inputs, output_hidden_states=True)
        res = torch.cat(res["hidden_states"][-3:-2], -1)[0].float().cpu()
    assert inputs["input_ids"].shape[-1] == len(word2ph)
    word2phone = word2ph
    phone_level_feature = []
    for i in range(len(word2phone)):
        repeat_feature = res[i].repeat(word2phone[i], 1)
        phone_level_feature.append(repeat_feature)

    phone_level_feature = torch.cat(phone_level_feature, dim=0)

    return phone_level_feature.T