Translation of comments from Chinese to English

Translation of comments from Chinese to English language.

app.py

@@ -1,6 +1,6 @@
 # OCR Translate v0.2
-# 创建人：曾逸夫
-# 创建时间：2022-07-19
+# 创建人：曾逸夫 (Founder: Zeng Yifu)
+# Creation time：2022-07-19
 
 import os
 
@@ -19,23 +19,23 @@ nltk.download punkt
 OCR_TR_DESCRIPTION = '''# OCR Translate v0.2
 <div id="content_align">OCR translation system based on Tesseract</div>'''
 
-# 图片路径
+# Image Path
 img_dir = "./data"
 
-# 获取tesseract语言列表
+# Get tesseract language list
 choices = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
 
 
-# 翻译模型选择
+# Translation model selection
 def model_choice(src, trg):
     # https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-pt-en
     # https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-pt
     # https://huggingface.co/unicamp-dl/translation-pt-en-t5
     # https://huggingface.co/unicamp-dl/translation-en-pt-t5
-    model_name = f"unicamp-dl/translation-{src}-{trg}-t5"  # 模型名称
+    model_name = f"unicamp-dl/translation-{src}-{trg}-t5"  # Model Name
 
-    #tokenizer = MarianTokenizer.from_pretrained(model_name)  # 分词器
-    #model = MarianMTModel.from_pretrained(model_name)  # 模型
+    #tokenizer = MarianTokenizer.from_pretrained(model_name)  # Tokenizer
+    #model = MarianMTModel.from_pretrained(model_name)  # Model
 
     tokenizer = T5Tokenizer.from_pretrained(model_name)
     model = T5ForConditionalGeneration.from_pretrained(model_name)
@@ -43,7 +43,7 @@ def model_choice(src, trg):
     return tokenizer, model
 
 
-# tesseract语言列表转pytesseract语言
+# Convert tesseract language list to pytesseract language
 def ocr_lang(lang_list):
     lang_str = ""
     lang_len = len(lang_list)
@@ -63,12 +63,12 @@ def ocr_tesseract(img, languages):
     return ocr_str
 
 
-# 清除
+# Clear
 def clear_content():
     return None
 
 
-# 复制到剪贴板
+# Copy to Clipboard
 def cp_text(input_text):
     # sudo apt-get install xclip
     try:
@@ -78,18 +78,18 @@ def cp_text(input_text):
         print(e)
 
 
-# 清除剪贴板
+# Clear Clipboard
 def cp_clear():
     pyclip.clear()
 
 
-# 翻译
+# Translate
 def translate(input_text, inputs_transStyle):
-    # 参考：https://huggingface.co/docs/transformers/model_doc/marian
+    # Reference：https://huggingface.co/docs/transformers/model_doc/marian
     if input_text is None or input_text == "":
         return "System prompt: There is no content to translate!"
 
-    # 选择翻译模型
+    # Selecting a translation model
     trans_src, trans_trg = inputs_transStyle.split("-")[0], inputs_transStyle.split("-")[1]
     tokenizer, model = model_choice(trans_src, trans_trg)
 
@@ -116,7 +116,7 @@ def main():
     with gr.Blocks(css='style.css') as ocr_tr:
         gr.Markdown(OCR_TR_DESCRIPTION)
 
-        # -------------- OCR 文字提取 --------------
+        # -------------- OCR Text Extraction --------------
         with gr.Blocks():
 
             with gr.Row():
@@ -153,7 +153,7 @@ def main():
                                 ["./data/test03.png", ["por"]]]
                 gr.Examples(example_list, [inputs_img, inputs_lang], outputs_text, ocr_tesseract, cache_examples=False)
 
-        # -------------- 翻译 --------------
+        # -------------- Translate --------------
         with gr.Blocks():
 
             with gr.Row():
@@ -171,11 +171,11 @@ def main():
             outputs_text,])
         clear_img_btn.click(fn=clear_content, inputs=[], outputs=[inputs_img])
 
-        # ---------------------- 翻译 ----------------------
+        # ---------------------- Translate ----------------------
         translate_btn.click(fn=translate, inputs=[outputs_text, inputs_transStyle], outputs=[outputs_tr_text])
         clear_text_btn.click(fn=clear_content, inputs=[], outputs=[outputs_text])
 
-        # ---------------------- 复制到剪贴板 ----------------------
+        # ---------------------- Copy to Clipboard ----------------------
         cp_btn.click(fn=cp_text, inputs=[outputs_tr_text], outputs=[])
         cp_clear_btn.click(fn=cp_clear, inputs=[], outputs=[])