add vocab_size to sentencepiece

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