Spaces:
Sleeping
Sleeping
File size: 3,547 Bytes
1f38345 db93ac2 1f38345 db93ac2 1f38345 db93ac2 1f38345 db93ac2 1f38345 db93ac2 1f38345 b107671 1f38345 b107671 db93ac2 1f38345 db93ac2 1f38345 0416c8c 1f38345 db93ac2 1f38345 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
# !/usr/bin/python
# -*- coding: utf-8 -*-
# @time : 2021/2/29 21:41
# @author : Mo
# @function: 文本纠错, 使用macro-correct
import os
os.environ["MACRO_CORRECT_FLAG_CSC_TOKEN"] = "1"
from macro_correct import correct
import gradio as gr
### 默认纠错(list输入)
text_list = ["真麻烦你了。希望你们好好的跳无",
"少先队员因该为老人让坐",
"机七学习是人工智能领遇最能体现智能的一个分知",
"一只小鱼船浮在平净的河面上"
]
text_csc = correct(text_list)
print("默认纠错(list输入):")
for res_i in text_csc:
print(res_i)
print("#" * 128)
"""
默认纠错(list输入):
{'index': 0, 'source': '真麻烦你了。希望你们好好的跳无', 'target': '真麻烦你了。希望你们好好地跳舞', 'errors': [['的', '地', 12, 0.6584], ['无', '舞', 14, 1.0]]}
{'index': 1, 'source': '少先队员因该为老人让坐', 'target': '少先队员应该为老人让坐', 'errors': [['因', '应', 4, 0.995]]}
{'index': 2, 'source': '机七学习是人工智能领遇最能体现智能的一个分知', 'target': '机器学习是人工智能领域最能体现智能的一个分支', 'errors': [['七', '器', 1, 0.9998], ['遇', '域', 10, 0.9999], ['知', '支', 21, 1.0]]}
{'index': 3, 'source': '一只小鱼船浮在平净的河面上', 'target': '一只小鱼船浮在平静的河面上', 'errors': [['净', '静', 8, 0.9961]]}
"""
def respond(
message,
history,
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
message_csc = correct([message])
target = message_csc[0].get("target", "")
errors = message_csc[0].get("errors", "")
response = target + " " + str(errors)
out = ""
for resp in response:
out += token
yield out
# response = ""
#
# for message in client.chat_completion(
# messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# token = message.choices[0].delta.content
#
# response += token
# yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="Macro-Correct", label="System message"),
# gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
# gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
# gr.Slider(
# minimum=0.1,
# maximum=1.0,
# value=0.95,
# step=0.05,
# label="Top-p (nucleus sampling)",
# ),
]
# title="Chinese Spelling Correction Model Macropodus/macbert4csc_v2",
# description="Copy or input error Chinese text. Submit and the machine will correct text.",
# article="Link to <a href='https://github.com/yongzhuo/macro-correct' style='color:blue;' target='_blank\'>Github REPO: macro-correct</a>",
)
if __name__ == "__main__":
demo.launch()
# demo.launch(server_name="0.0.0.0", server_port=8087, share=False, debug=True) |