-
 2018 Microsoft Corporati…
-
# MacBERT：MLM as correction BERT | hongyuntw
macBERT - Revisiting Pre-Trained Models for Chinese Natural Language Processing
[http://localhost:1313/posts/macbert/](http://localhost:1313/posts/macber…
-
import os
import numpy as np
from bert4keras.backend import keras, K
from bert4keras.models import build_transformer_model
from bert4keras.tokenizers import Tokenizer
from bert4keras.snippets imp…
-
Model name 'bert-base-uncased' was not found in model name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased,…
-
启动命令：
`python api_v2.py -a 0.0.0.0 -p 7860 -c GPT_SoVITS/configs/tts_infer.yaml`
tts_infer.yaml:
`
custom:
bert_base_path: GPT_SoVITS/pretrained_models/chinese-roberta-wwm-ext-large
cnh…
-
import torch
from transformers import BertForTokenClassification, BertTokenizer, AdamW
# 设定设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# 加载预训练的BERT模型和分词器
model_name = 'b…
-
您好，非常感谢您的代码：
我在调试的时候，下载了谷歌的chinese_base压缩包，解压后，用https://github.com/huggingface/pytorch-pretrained-BERT/tree/1de35b624b9d7998feb4d518e4f7e8e53abac4e1的方法转化成bin。或者是用https://github.com/NLPScott/bert-…
-
我的是do_train, do_eval, do_predict同时为true的时候的f1正常； 训练结束后想再做predict则f1为0.
我的命令行如下:
bert-base-ner-train --do_train=False --do_eval=False --do_predict=True --data_dir=data1/ --predict_batch_siz=16 --max_…