EricaCorral's picture
Update app.py
e27c282
raw
history blame
1.44 kB
from pypinyin import pinyin
from transformers import MarianMTModel, MarianTokenizer
from LAC import LAC
import gradio as gr
import torch
model = MarianMTModel.from_pretrained("Helsinki-NLP/opus-mt-zh-en")
model.eval()
tokenizer = MarianTokenizer.from_pretrained("Helsinki-NLP/opus-mt-zh-en")
lac = LAC(mode="seg")
def make_request(chinese_text):
with torch.no_grad():
generated_tokens = model.generate(**tokenizer(chinese_text, return_tensors="pt", padding=True))
return [tokenizer.decode(generated_tokens, skip_special_tokens=True) for t in translated]
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 Helsinki Research's Chinese to English model. Makes for extremely FAST translations.",
inputs=gr.inputs.Textbox(lines=5, placeholder="Enter text in Chinese"),
outputs="text")
iface.launch()