yujunlhz

Results 5 comments of yujunlhz

For ASR, if I set num_cnn_layers = 0, Invalid argument: Matrix size-incompatible: In[0]: [96,1056], In[1]: [1120,4096]

@jonathanasdf would you help with this issue? For ASR, if I set num_cnn_layers = 0, Invalid argument: Matrix size-incompatible: In[0]: [96,1056], In[1]: [1120,4096]

For ASR, if I set num_cnn_layers = 0, Invalid argument: Matrix size-incompatible: In[0]: [96,1056], In[1]: [1120,4096]

Ah, it should be ep.input_shape = [None, None, 32, 3]. I had thought that [None, None, 32, 3] can be change to [None, None, 96, 1] automatically. thanks

For ASR, if I set num_cnn_layers = 0, Invalid argument: Matrix size-incompatible: In[0]: [96,1056], In[1]: [1120,4096]

Hey @jonathanasdf , if I wish to use MFCC feature instead fbank feature, I need to insert a few projection layers in front of the BLSTM layers in stead of...

Why Lingvo is so slow when training Librispeech960Wpm on a host with 6 GPUs

I even don't know what exact they mean. I guess from their name: saver_max_to_keep : keep this number of history models on disk. if it not set, many history models...

error when PytorchStreamReader failed reading file

it turn out that Linv.pt was generated with a another version. thanks