tts-9nine / text /english_bert_mock.py
qxdn's picture
Upload 17 files
3b404f3
import sys
import torch
from transformers import DebertaV2Model, DebertaV2Tokenizer
from config import config
LOCAL_PATH = "./bert/deberta-v3-large"
#LOCAL_PATH = 'microsoft/deberta-v2-xlarge'
tokenizer = DebertaV2Tokenizer.from_pretrained(LOCAL_PATH)
models = dict()
def get_bert_feature(text, word2ph, device=config.bert_gen_config.device):
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] = DebertaV2Model.from_pretrained(LOCAL_PATH).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) == res.shape[0], (text, res.shape[0], 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