From 5ffbe8ba5ce6146188a64e4427fa42d781921920 Mon Sep 17 00:00:00 2001
From: Aayush <aayushyadav96@gmail.com>
Date: Mon, 19 Nov 2018 19:13:55 +0530
Subject: [PATCH] add vocab_size to sentencepiece

---
 ulmfit/pretrain_lm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ulmfit/pretrain_lm.py b/ulmfit/pretrain_lm.py
index 0847ca6..06853a0 100644
--- a/ulmfit/pretrain_lm.py
+++ b/ulmfit/pretrain_lm.py
@@ -70,7 +70,7 @@ def pretrain_lm(dir_path, lang='en', cuda_id=0, qrnn=True, subword=False, max_vo
         read_file(trn_path, 'train')
         read_file(val_path, 'valid')
 
-        sp = get_sentencepiece(dir_path, trn_path, name)
+        sp = get_sentencepiece(dir_path, trn_path, name, vocab_size=max_vocab)
 
         data_lm = TextLMDataBunch.from_csv(dir_path, **sp)
         itos = data_lm.train_ds.vocab.itos