-
**Describe the bug**
When loading Flux >=0.13.14 there is an init error for loading cuDNN (see related Flux issue: https://github.com/FluxML/Flux.jl/issues/2232). The error comes from loading the…
-
In #140 I observed the transducer val loss converging but the accuracy staying the same for the english-medium dataset in the sigmorphn-2017 shared task dataset. When predicting, it seemed to learn to…
-
Guys,
I have been thinking about this for a few days and I think I am getting close to how we can solve this...
We tend to train on only one dataset (e.g. Librispeech); we rarely try to fold in o…
-
Can you help me to train model.
When I try train model with car dataset, I met this error
 when CUDA_VISIBLE_DEVICES=0,1 causes a memory leak in eval_step.
python…
-
`torchaudio` is an extension library for PyTorch, designed to facilitate audio processing using the same PyTorch paradigms familiar to users of its tensor library. It provides powerful tools for audio…
-
As a result of https://github.com/rwth-i6/returnn/issues/1120 and https://github.com/rwth-i6/returnn/issues/1264, we want to move core functions over to RETURNN, as this should become the common compa…
-
I'm looking into how to convert my old `DatasetConfig`-based datasets to the new `Dataset` interface (#231).
What I'm missing:
- I want to combine train, dev, devtrain somehow together. This is …
-
Notice: In order to resolve issues more efficiently, please raise issue following the template.
（注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）
## 🐛 Bug
使用1.x版本funasr，跑aishell训练例子时，在stage 1 compute_audio_cmv…