pychain_example
pychain_example copied to clipboard
YiwenShaoStephen
Hello, I encountered a problem these days while running the training scripts. After initializing the dataset and model, the model started to train and a lot of errors popped out...
Hi， when i use the mini_librispeech in run.sh : Stage 5 Here is a problem. Initializing dataset... 100%|███████████████████████████████████████████████████████████████████████████| 1519/1519 [00:01
I am getting the following issue while running WSJ script ImportError: /usr/local/lib/python3.6/dist-packages/simplefst-0.0.0-py3.6-linux-x86_64.egg/simplefst.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN3fst9FstHeader4ReadERSiRKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEEb
The model seems just using 1 cuda device. I'm using my own machine with 4 card , and set the cmd.sh as: export train_cmd="run.pl --mem 8G" export cuda_cmd="run.pl --mem 8G...
To Yiwen Shao, I request this commit for bugfix in mini_librispeech and wsj recipe. Please check and approve it. Thanks. Hosung Park.
我采用miniLibrispeech作为训练和测试语音数据集进行测试，使用example中的tdnn作为训练模型，整个run的流程并未报错，但是最终wer结果为100%。 $WER 100.00%[20138/20138,0 ins, 20138 del, 0sub]
