text/chinese_bert.py

import torch
import sys
from transformers import AutoTokenizer, AutoModelForMaskedLM
import os
#如果D:\pyprojs\Bert-VITS2\bert\chinese-roberta-wwm-ext-large\pytorch_model存在就用这个
local_bert = False
if os.path.exists("./bert/chinese-roberta-wwm-ext-large/pytorch_model.bin"):
    local_bert = True


tokenizer = AutoTokenizer.from_pretrained("./bert/chinese-roberta-wwm-ext-large") if  local_bert else AutoTokenizer.from_pretrained("hfl/chinese-roberta-wwm-ext-large")

models = dict()


def get_bert_feature(text, word2ph, device=None):
    if (
        sys.platform == "darwin"
        and torch.backends.mps.is_available()
        and device == "cpu"
    ):
        device = "mps"
    if not device:
        device = "cuda"
    if device not in models.keys():
        models[device] = AutoModelForMaskedLM.from_pretrained(
            "./bert/chinese-roberta-wwm-ext-large"
        ).to(device) if local_bert else AutoModelForMaskedLM.from_pretrained(
            "hfl/chinese-roberta-wwm-ext-large"
        ).to(device)
    with torch.no_grad():
        inputs = tokenizer(text, return_tensors="pt")
        for i in inputs:
            inputs[i] = inputs[i].to(device)
        res = models[device](**inputs, output_hidden_states=True)
        res = torch.cat(res["hidden_states"][-3:-2], -1)[0].cpu()

    assert len(word2ph) == len(text) + 2
    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


if __name__ == "__main__":
    import torch

    word_level_feature = torch.rand(38, 1024)  # 12个词,每个词1024维特征
    word2phone = [
        1,
        2,
        1,
        2,
        2,
        1,
        2,
        2,
        1,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        2,
        1,
        1,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        2,
        1,
        2,
        2,
        2,
        2,
        1,
    ]

    # 计算总帧数
    total_frames = sum(word2phone)
    print(word_level_feature.shape)
    print(word2phone)
    phone_level_feature = []
    for i in range(len(word2phone)):
        print(word_level_feature[i].shape)

        # 对每个词重复word2phone[i]次
        repeat_feature = word_level_feature[i].repeat(word2phone[i], 1)
        phone_level_feature.append(repeat_feature)

    phone_level_feature = torch.cat(phone_level_feature, dim=0)
    print(phone_level_feature.shape)  # torch.Size([36, 1024])