-
I have a CPU model that produces different outputs for the same strings at different times.
I think it could be related to the bug from https://github.com/OpenNMT/CTranslate2/issues/546 where batch…
-
Hello,
I am trying to load my finetuned model with whisperX but I am getting this error:
Unsupported model binary version. This executable supports models with binary version v6 or below, but th…
-
您好，请问您能发我一份inspec数据集吗，我使用kp20k感觉模型泛化能力不行，就是我自己训练机拟合还可以，测试集跑一下就太低了，谢谢
ruizi updated
4 years ago
-
With the `keep_checkpoint` option we can specify how many checkpoints should be kept. However, the checkpoints are just saved sequentially and never ordered. That means that if your best performing mo…
-
You guys really did an excellent work with high scalability. Better than OpenNMT in my opinion :)
Copy mechanism could greatly enhance the performance of Seq2Seq model, would you guys implement a d…
-
Hi,
I see that this implementation is lacking masked attention on encoder. Input_lengths should be passed to decoder (not just encoder) in order to compute this. OpenNMT already provided this in func…
-
I am really happy seeing question generation work like this. However, i am not familiar with torch, is there any resource written in tensrflow that can reproduce your work?
-
### 🐛 Describe the bug
I am having serious doubt on the 1.13 Adam(fused=true) implementation.
First it should be faster than fused=False, in our case it is not, but also the numerical seems off.
…
-
Hi Steve,
I found that if I use the build_vocab script in current OpenNMT_py version (2.0.0), the output vocab file is not compatible with the ggnn encoder. It will raise such a error.
```
Trac…
-
我看到了你們在這裡發佈的訊息，與把 Abstractive summarization 整合進 library 覺得非常好
https://chinesenlp.xyz/docs/text_summarization.html
一年前我在碩士期間研究了 Chinese summarization
這是我的 Paper
當初發現了 LCSTS 的資料集上有缺陷，在 training …