Upload 2 files

app.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+
+import gradio as gr
+import operator
+import torch
+from transformers import BertTokenizer, BertForMaskedLM
+
+
+# pretrained_model_name_or_path = "Macropodus/macbert4mdcspell_v2"
+pretrained_model_name_or_path = "D:/Anacoda3/envs/py38/Lib/site-packages/macro_correct/output/text_correction/macbert4mdcspell_v2"
+tokenizer = BertTokenizer.from_pretrained(pretrained_model_name_or_path)
+model = BertForMaskedLM.from_pretrained(pretrained_model_name_or_path)
+vocab = tokenizer.vocab
+
+
+def func_macro_correct(text):
+    with torch.no_grad():
+        outputs = model(**tokenizer([text], padding=True, return_tensors='pt'))
+
+    def flag_total_chinese(text):
+        """
+        judge is total chinese or not, 判断是不是全是中文
+        Args:
+            text: str, eg. "macadam, 碎石路"
+        Returns:
+            bool, True or False
+        """
+        for word in text:
+            if not "\u4e00" <= word <= "\u9fa5":
+                return False
+        return True
+
+    def get_errors(corrected_text, origin_text, unk_tokens=[], know_tokens=[]):
+        """Get new corrected text and errors between corrected text and origin text
+        code from:  https://github.com/shibing624/pycorrector
+        """
+        errors = []
+        unk_tokens = unk_tokens or [' ', '“', '”', '‘', '’', '琊', '\n', '…', '擤', '\t', '玕', '', '，']
+
+        for i, ori_char in enumerate(origin_text):
+            if i >= len(corrected_text):
+                continue
+            if ori_char in unk_tokens or ori_char not in know_tokens:
+                # deal with unk word
+                corrected_text = corrected_text[:i] + ori_char + corrected_text[i + 1:]
+                continue
+            if ori_char != corrected_text[i]:
+                if not flag_total_chinese(ori_char):
+                    # pass not chinese char
+                    corrected_text = corrected_text[:i] + ori_char + corrected_text[i + 1:]
+                    continue
+                if not flag_total_chinese(corrected_text[i]):
+                    corrected_text = corrected_text[:i] + corrected_text[i + 1:]
+                    continue
+                errors.append([ori_char, corrected_text[i], i])
+        errors = sorted(errors, key=operator.itemgetter(2))
+        return corrected_text, errors
+
+    _text = tokenizer.decode(torch.argmax(outputs.logits[0], dim=-1), skip_special_tokens=True).replace(' ', '')
+    corrected_text = _text[:len(text)]
+    corrected_text, details = get_errors(corrected_text, text, know_tokens=vocab)
+    print(text, ' => ', corrected_text, details)
+    return corrected_text + ' ' + str(details)
+
+
+if __name__ == '__main__':
+    print(func_macro_correct('他法语说的很好，的语也不错'))
+
+    examples = [
+        "夫谷之雨，犹复云之亦从的起，因与疾风俱飘，参于天，集于的。",
+        "机七学习是人工智能领遇最能体现智能的一个分知",
+        '他们的吵翻很不错，再说他们做的咖喱鸡也好吃',
+        "抗疫路上，除了提心吊胆也有难的得欢笑。",
+        "我是练习时长两念半的鸽仁练习生蔡徐坤",
+        "清晨，如纱一般地薄雾笼罩着世界。",
+        "得府许我立庙于此，故请君移去尔。",
+        "他法语说的很好，的语也不错",
+        "遇到一位很棒的奴生跟我疗天",
+        "五年级得数学，我考的很差。",
+        "我们为这个目标努力不解",
+        '今天兴情很好',
+    ]
+
+    gr.Interface(
+        func_macro_correct,
+        inputs='text',
+        outputs='text',
+        title="Chinese Spelling Correction Model Macropodus/macbert4mdcspell_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>",
+        examples=examples
+    ).launch(server_name="0.0.0.0", server_port=8036, share=False, debug=True)
+
+

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+transformers
+torch
+macro-correct