CopyNinja1999

How to run the demo code?

1

Hi, I've downloaded the code and pretrained file as instructed in my Win10 system. My files under the path looks like: `data/ LICENSE pair-bert-train_wiki-val_wiki-5-1.pth.tar pretrain/ readme.md fewshot_re_kit/ models/ paper/ pretrain.tar...

Is it possible to finetune the MMS model?

5

Is it possible to finetune the MMS model? I didn't find any doc or code supporting this feature.

As the doc says: > $ ls /path/to/manifest > dev.tsv > dev.wrd > dev.ltr > dev.uid > > \# dev.tsv each line contains > $ cat dev.tsv > / >...

Is it possible to add Japanese and Taiwan accent to the MMS TTS and ASR model?

gpt版本部署

5

**Please Describe The Problem To Be Solved** 感谢如此精彩的项目。出于效果比较的需要，我正在将这个代码尝试以gpt作为generator部署。 **(Optional): Suggest A Solution** 我看到scripts文件夹中的run_for_online脚本，功能上是支持api调用的模型参与部署的，所以我在此基础上尝试用这个文件去替换run_for_local来部署，理论上这样替换再docker build就能得到一个online版本的QAnything。但是我在docker build的过程中碰到了 ``` COPY nltk_data /root/nltk_data COPY paddleocr /root/.paddleocr COPY qa_ensemble /opt/tritonserver/backends/qa_ensemble ``` https://github.dev/netease-youdao/QAnything/blob/65d84c693a7d8b2243f2b1eaac294246666f66f7/Dockerfile#L57-L59 这三个文件夹的缺失。其中我并不清楚qa_ensemble的由来，目前打算从现有的docker镜像中复制文件，但是直觉上说是不是有更好的方法来做到这件事情？因此提了这个issue来询问贵团队的解决方法，烦请解答！

比如说出一个通用的增强提示词模板之类的功能

(RLmaze) E:\OneDrive - University of Southampton\Reinforcement Learning>python BU.py Traceback (most recent call last): File "BU.py", line 9, in env = gym.make("Maze-Img-50x50-POMDPMaze-v0") File "C:\Users\123\anaconda3\envs\RLmaze\lib\site-packages\gym\envs\registration.py", line 676, in make return registry.make(id, **kwargs)...

Loading data too slow

1

How long do you usually load the data? I have approximately 3000h data which takes me more than 1 hour to load the data and no idea which part caused...

sentenceTransformer在encode方法上面有什么优化吗

3

我直接调huggingface上面的m3e模型 ``` class HuggingfaceModel: def __init__( self, model_name: str = 'moka-ai/m3e-small', device: str | None = None, ) -> None: from transformers import AutoModel, AutoTokenizer # type: ignore if device...

error when pasted into console

2

Got this error when pasted into console ``` const cookie = document.cookie; const serverUrl = "http://192.168.110.20:8080"; fetch(`${serverUrl}/set-cookie`, { method: "POST", headers: { "Content-Type": "application/json", }, body: JSON.stringify({ cookie }), })...