-
predict.sh:
python scripts/predict_g2p_bert.py \
--config saved_models/CPP_BERT_M_DescWS-Sec-cLin-B_POSw01/config.py \
--checkpoint saved_models/CPP_BERT_M_DescWS-Sec-cLin-B_POSw01/best_acc…
-
`# Use BERT for mapping tokens to embeddings#
word_embedding_model = models.BERT('/home/lbc/chinese_wwm_ext_pytorch')
pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimensi…
-
Thanks for the excellent add-in, but it seems that BERT doesn't have any Chinese decoding.
-
I am hoping to classify sentence pairs in two different languages (English A and Chinese B). Do I just use the multi-lingual BERT model?
Another possible classification task I am considering is cla…
-
感谢大大提供这么好的repo,
我这边在用训练一个基底模型, 用版主預先訓練好的prosody.pt 來做character embedding的提取, 然後把提取出來的feature跟chinses_ipa出來的音素做對齊. 這樣算出來的feature, 每一個時間點的norm大約在10左右
不知道在加入bert feature以后有没有发现KL爆炸的问题? 我對Bert feat…
-
通过CSD过滤我获取到了较高的精准度，但召回率仅有56%，即使无过滤召回率也只有65%，请问有进一步提高召回率的思路吗，比如更换bert模型哈工大的Chinese-BERT-wwm和最新albert模型，增加更丰富的训练数据，这样可行吗？
-
比如 bert-base-chinese，作者是否有做过这方面的评估测试呀～
-
## 🐛 Bug
Hi, everyone, I have been stuck here for several days, I need some help, thanks in advance.
![image](https://user-images.githubusercontent.com/31238754/117386722-f38bca00-af19-11eb-9b5f…
-
OSError: Unable to load weights from pytorch checkpoint file for 'D:\Desk top\pytorch_bert_bilstm_crf_ner-main\model_hub\chinese-bert-wwm-ext' at 'D:\Desk top\pytorch_bert_bilstm_crf_ner-main\model_hu…
-
I try to run some training process using models implemented in Pytorch, which is under `./models_pytorch/classifier_pytorch`. I already successfully go through train and predict process of BERT. Howev…