search

lucasnewman / best-rq-pytorch

Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.
MIT License
71 stars 7 forks source link

What is the final result like? #3

Open a897456 opened 9 months ago

a897456 commented 9 months ago

What is the final result like? Can you take a screenshot to show it? this is my result: trainable parameters: 657398946 training with dataset of 2052 samples and validating with randomly splitted 109 samples do you want to clear previous experiment checkpoints and results? (y/n) y 0: loss: 6.983 0: valid loss 5.440 0: saving model to results

Process end, code exit -1073741819 (0xC0000005)

lucasnewman commented 9 months ago

That's a pretty big model with 657M parameters, so you may be running out of memory. You could try reducing the size of the Conformer network — if you share your training code it will be easier to debug.

a897456 commented 9 months ago

That's a pretty big model with 657M parameters, so you may be running out of memory. You could try reducing the size of the Conformer network — if you share your training code it will be easier to debug.

I did nothing but just change the dataset_folder to "C:/Users/User1/Desktop/hifi-gan-master/LJSpeech-1.1/wav_test". And I found that when step becomes 1, the program exits directly from this breakpoint. image