|
import sys |
|
|
|
import torch |
|
from transformers import DebertaV2Model, DebertaV2Tokenizer |
|
|
|
tokenizer = DebertaV2Tokenizer.from_pretrained("./bert/deberta-v3-large") |
|
|
|
models = dict() |
|
|
|
|
|
def get_bert_feature(text, word2ph, device="cuda"): |
|
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("./bert/deberta-v3-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() |
|
|
|
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 |
|
|
