This commit is contained in:
marcoyang 2024-01-09 15:39:43 +08:00
parent f42258caf8
commit 083744d894

View File

@ -77,7 +77,7 @@ The next step is to train the RNNLM model. The training command is as follows:
--use-fp16 0 \
--tie-weights 1 \
--embedding-dim 2048 \
--hidden_dim 2048 \
--hidden-dim 2048 \
--num-layers 3 \
--batch-size 300 \
--lm-data rnn_lm/data/lang_bpe_500/sorted_lm_data.pt \
@ -93,12 +93,3 @@ The next step is to train the RNNLM model. The training command is as follows:
.. note::
The training of RNNLM can take a long time (usually a couple of days).