Transfer Learning epoch error

Hi, i am using a pre-trained(transfer learning) model as a base for my new speech data, but while training for a single epoch , it should have stopped after one epoch ,but it is not happening , model gets trained beyond one epoch, can anyone help me out, why is it happening?

–checkpoint_dir ‘/home/lee/tmp/downloads/deepspeech-0.5.1-checkpoint’
–train_files ‘/home/lee/tmp/DS_TRAINING/TRAIN/train.csv’
–dev_files ‘/home/lee/tmp/DS_TRAINING/DEV/dev.csv’
–test_files ‘/home/lee/tmp/DS_TRAINING/TEST/test.csv’
–train_batch_size 1
–dev_batch_size 1
–test_batch_size 1 \
–n_hidden 2048 \
–epochs 1
–export_dir ‘/home/lee/tmp/EXPORT’ \
–alphabet_config_path ‘/home/lee/tmp/downloads/deepspeech-0.5.1-models/alphabet.txt’
–lm_binary_path ‘/home/lee/tmp/downloads/deepspeech-0.5.1-models/lm.binary’
–lm_trie_path ‘/home/lee/tmp/downloads/deepspeech-0.5.1-models/trie’

not sure, but if I remember correctly, it starts at 0, so “epochs 1” will run for 2 epochs.

Have you tried 0 as a value?

1 Like