diff --git a/README.md b/README.md
index be47b61..6180d1e 100644
--- a/README.md
+++ b/README.md
@@ -59,7 +59,7 @@ print("Label probs:", text_probs)  # prints: [[1.0, 0.0, 0.0]]
 ```
 
 # Model architecture
-The model was trained  a ViT-B/16 Transformer architecture as an image encoder and uses a 12-layer RoBERTa as a text encoder. The text encoder was trained upon the pre-trained Japanese RoBERTa model [rinna/japanese-roberta-base](https://huggingface.co/rinna/japanese-roberta-base) with the same sentencepiece tokenizer.
+The model was trained  a ViT-B/16 Transformer architecture as an image encoder and uses a 12-layer RoBERTa as a text encoder. The text encoder was trained upon the Japanese pre-trained RoBERTa model [rinna/japanese-roberta-base](https://huggingface.co/rinna/japanese-roberta-base) with the same sentencepiece tokenizer.
 
 # Training
 The model was trained on [CC12M](https://github.com/google-research-datasets/conceptual-12m) translated the captions to Japanese.