🍶 baseline

README.md

@@ -1,37 +1,13 @@
 ---
 title: Modern Chinese To Ancient Translate Wenyanwen
-emoji: 😻
+emoji: 🍶
 colorFrom: gray
-colorTo: gray
+colorTo: cyan
 sdk: streamlit
 app_file: app.py
-pinned: false
+pinned: true
 ---
 
-# Configuration
-
-`title`: _string_  
-Display title for the Space
-
-`emoji`: _string_  
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_  
-Can be either `gradio` or `streamlit`
-
-`sdk_version` : _string_  
-Only applicable for `streamlit` SDK.  
-See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
-
-`app_file`: _string_  
-Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
-Path is relative to the root of the repository.
-
-`pinned`: _boolean_  
-Whether the Space stays on top of your list.
+# Modern Chinese To Ancient Translate Wenyanwen
+* Huggingface Model's Model: [wenyanwen-chinese-translate-to-ancient](https://huggingface.co/raynardj/wenyanwen-chinese-translate-to-ancient)
+* [GitHub](https://github.com/raynardj/yuan)

app.py

@@ -0,0 +1,45 @@
+from transformers import (
+  EncoderDecoderModel,
+  AutoTokenizer
+)
+import torch
+
+PRETRAINED = "raynardj/wenyanwen-chinese-translate-to-ancient"
+
+def inference(text):
+    tk_kwargs = dict(
+      truncation=True,
+      max_length=128,
+      padding="max_length",
+      return_tensors='pt')
+   
+    inputs = tokenizer([text,],**tk_kwargs)
+    with torch.no_grad():
+        return tokenizer.batch_decode(
+            model.generate(
+            inputs.input_ids,
+            attention_mask=inputs.attention_mask,
+            num_beams=3,
+            bos_token_id=101,
+            eos_token_id=tokenizer.sep_token_id,
+            pad_token_id=tokenizer.pad_token_id,
+        ), skip_special_tokens=True)
+
+import streamlit as st
+
+st.title("Wenyanwen Translator")
+st.markdown("""
+# Translate from Chinese to Ancient Chinese / 还你古朴清雅壮丽的文言文, 这[github](https://github.com/raynardj/yuan)
+""")
+
+@st.cache
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained(PRETRAINED)
+    model = EncoderDecoderModel.from_pretrained(PRETRAINED)
+    return tokenizer, model
+
+tokenizer, model = load_model()
+
+text = st.text_area("轻轻地我走了，正如我轻轻地来。我挥一挥衣袖，不带走一片云彩。")
+
+st.write(inference(text)[0])