Create app.py

app.py

@@ -0,0 +1,40 @@
+from pypinyin import pinyin
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from LAC import LAC
+import gradio as gr
+import torch
+
+model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-zh-en")
+model.eval()
+tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-zh-en")
+lac = LAC(mode="seg")
+
+def make_request(chinese_text):
+  with torch.no_grad():
+      encoded_zh = tokenizer.prepare_seq2seq_batch([chinese_text], return_tensors="pt")
+      generated_tokens = model.generate(**encoded_zh)
+      return tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
+
+def generatepinyin(input):
+  pinyin_list = pinyin(input)
+  pinyin_string = ""
+  for piece in pinyin_list:
+    pinyin_string = pinyin_string+" "+piece[0]
+  return pinyin_string
+
+def generate_response(Chinese_to_translate):
+    response = []
+    response.append([Chinese_to_translate,make_request(Chinese_to_translate),generatepinyin(Chinese_to_translate)])
+    segmented_string_list = lac.run(Chinese_to_translate)
+    for piece in segmented_string_list:
+        response.append([piece,make_request(piece),generatepinyin(piece)])
+    return response
+
+iface = gr.Interface(
+    fn=generate_response,
+    title="Chinese to English",
+    description="Chinese to English with a state-of-the-art model (facebook-research m2m-100 1.2B)",
+    inputs=gr.inputs.Textbox(lines=5, placeholder="Enter text in Chinese"),
+    outputs="text")
+
+iface.launch()