Yu Wu (吴俣)
Hi, It looks like the code cannot run until now? I also get the error when I run this code.
Hi, when will you release the code for 'Deep Reinforcement Learning for Dialogue Generation'? Thank you in advanced.
Data structure is shown in the PreProcess.py. That file illustrates how to preprocess plain text containing question and answering.
> I have finished training and decoding in AISHELL-1 dataset and got cer=12.4% in test set，and i found that my model.json which uses the default config is different from the...
> Thank you very much. Chengyi told me her model achieves 6.0 on AISELL-1 yesterday with a conformer architecture as an encoder.
Hi, please email me ([email protected]), and I will send you the rest data
@guanxingke you should serialize the object named "params" which stored the parameter in the model. When you predict a new document classification, you should reconstruct the neutral network and set...
@guanxingke No, I mean both cnn parameters and mlp features. I used CPickle to stored the params successfully. savefile = file('obj.save', 'wb') cPickle.dump(params,savefile,protocol=cPickle.HIGHEST_PROTOCOL) Furthermore, when you use the stored feature....
> How long would the training take, for example in the 16x V100 case? It takes 4 days with 16x 32G V100. I did not train it with LibriTTS, but...