Slyne Deng

Do you mind checking this issue: https://github.com/triton-inference-server/server/issues/3777#issuecomment-1027418452 ? There's an invalid pointer issue related to kaldifeat + pybind.

Hi Qingfeng, This repo is a toy example and it is out of date. The packages required may have big changes and updates. Also I see many people nowadays use...

Hi @travisCxy 有服务器端的log吗 另外我没有测过 >1GB 的语言模型 如果方便的话 你可以分享一下你的语言模型方便我测试吗? 如果怕有隐私问题，可以构建成binary: ``` build_binary -q 8 trie lm.arpa lm01111.bin ``` 也可以用这个[脚本](https://github.com/wenet-e2e/wenet/blob/0eca1d0daa0198c438e52c2bdf5dc1d8ca7a4861/wenet/bin/recognize_onnx.py)先本机测一下 在这个脚本里加语言模型的方法可以参照: https://github.com/Slyne/ctc_decoder/blob/master/swig/test/test_en.py#L51 ``` # 初始化语言模型打分 alpha = 0.5 beta = 0.5 lm_path...

记录一下问题: 主要是语言模型构建问题 @travisCxy 用的是srilm构建的 这个项目只支持kenlm的语言模型

> 你您好，请问这个在windows可以安装吗 没试过..

> At first glance this seems excessive details are leaking about quantization compared to before. Is all of this because the model is not exporting length information ? Yes. In...

如果语言模型的文本是这样的就可以: ``` 你 刚 刚 吃 K F C 了 ？ ```

> Resolved. > > The wrong output shape is provided. It may be caused by convert.py @yzmyyff Thank you. Could you provide the link to a train.yaml/config.yaml ? I found...

> Sure, here are these two files https://gist.github.com/yzmyyff/36fff2a3be9b57870034b0787e70f5ee > > How about raising a warning if no shape is provided. It'll be better to extract the output shape from onnx...

> This bug still exists in the current main branch how to fix it？ Please give it a try in Pytorch 1.9 or the latest Pytorch as mentioned: https://github.com/pytorch/pytorch/issues/71408. Another...