You signed in with another tab or window.Reloadto refresh your session.You signed out in another tab or window.Reloadto refresh your session.You switched accounts on another tab or window.Reloadto refresh your session.Dismiss alert
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Only numpy is used to implement the neural network from scratch, including the back propagation formula derivation process;Numpy constructs the full connection layer, convolution layer, pooling layer and Flatten layer;As well as image classification cases and fine tuning network cases, they are continuously updated