uuuuuvp

> Hey bro, have you solved that? Got some similar problems. so am i, so many warnings...... the docker environments that i pulled don't work at all...

> > > 话说数据集换了的话，稀疏的那几个参数需要怎么配置呢，原始的话可能10个epoch就到了 > > > > > > 我没有改其他的东西，只是把epochs调大了，因为我初始的loss会在5.2左右需要更多的轮数，不知道为什么大家的第一轮都只有3左右 > > 我也是，第一轮5.3，跑了二三十轮还有4.6 我跑了120个epoch，最后还是5.1，已经懵圈了

_libgcc_mutex 0.1 conda_forge conda-forge _openmp_mutex 4.5 2_gnu conda-forge ca-certificates 2024.7.4 hbcca054_0 conda-forge certifi 2024.7.4 pypi_0 pypi charset-normalizer 3.3.2 pypi_0 pypi idna 3.7 pypi_0 pypi ld_impl_linux-64 2.40 hf3520f5_7 conda-forge libffi 3.4.2...

> 如果有人仍然遇到此问题，解决方案如下： > > 1. 转到 https://github.com/xiph/LPCNet/ 并克隆存储库 > 2. 在运行任何内容之前，请执行以下操作`git checkout -b new_branch 2139eb3` > 3. 根据以下标准运行一切`Readme.md` > 4. 成功 >我尝试了你的方法，没有成功

> Just as [#208](https://github.com/xiph/LPCNet/issues/208) you can do: `git reset --hard 3000fa24717cbb68291e5bc589da0db351b51dec` then complie, it works for me. man, it's helps me a lot

> prepend __attribute__((visibility("default"))) before the line 57 of freq.h fixed the issue which looks like: __attribute__((visibility("default"))) float lpc_from_cepstrum(float *lpc, const float *cepstrum); Bro, can I take a look at your...

> I changed the sample rate from 16k to 32k and modify the NB_BANDS, but I wonder how to generate the ceps codebook? Bro, have you solved this problem? I...

> When I change the dataset and wanna train a new model, should I change the ceps_codebooks.c at first？ > > I didn't change the ceps_bodebooks.c at all, and only...