-
我尝试了用google的chinese-bert模型 和 zhuiyi的wobert-plus模型，来进行预测句子中[MASK]的候选词的实验，发现wobert-plus得到的结果都是停用词，请教一下哪里操作错误了。
predict函数：
```python
def TopCandidates(token_ids, i, topn=64):
"""用语言模型给出第i个位置的to…
-
### What is your question?
How much GPU memory is required to train a BERT model?
For start I have this commands from your readme file ```adaseq train -c demo.yaml``` and faced with Out of memory…
-
想请教一下ONNX导出后不知道怎么用，仓库里由哪些代码可以用来参考呢？
使用`onnx_export.py`成功导出了v1的模型，一共有：
```
- t2s_encoder.onnx
- fsdec.onnx
- t2s_sdec.onnx
- vits.onnx
- config.json
```
但是没看明白要怎么用它们😂
-
Hi, I'd run into "RuntimeError: CUDA error: device-side assert triggered" error when I attempted to run your code on a Chinese dataset.
The log is as follows:
/pytorch/aten/src/THC/THCTensorIn…
-
你好，我在复现您的实验（没有进行任何修改）的时候在主干网络的训练时准确率是逐渐提高的，在蒸馏阶段验证集和测试集的acc每一个epoch都和主干网络的最后一个epoch相同，请问是我哪里出错了吗？
-
Thank you very much for sharing the receipt for fine tuning the LJSpeech dataset. I'm wondering if I can still train a new voice with a smaller dataset. With other model architecture I was able to c…
-
I have a question because there is a difference in the value of the author's top-k recall and my top-k recall.
When validating with the checkpoint posted by the author, the result value as shown in …
-
Hey @FreddeFrallan, amazing contribution. I wanted to ask if it is possible to share the code of translating and generating the CLIP embedding dataset. I wanted to train in few languages which were no…
-
### Issue Description
当我模仿官方的实例时(https://shap.readthedocs.io/en/latest/example_notebooks/api_examples/plots/text.html#Single-实例文本图）运行SHAP时，我总是得到错误标题。这是我的代码。我可以问一下大家哪里出了问题吗？
When I imitate the offici…
-
The codes in line 53 in LabelAccuracyEvaluator.py :
_, prediction = model(features[0])
It does not work. When I run this code,error occurs.