Create app.py

app.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+
+import gradio as gr
+import operator
+import torch
+from transformers import BertTokenizer, BertForMaskedLM
+
+# 使用私有模型和分詞器
+model_name_or_path = "DeepLearning101/Corrector101zhTW"
+auth_token = "Corrector101zhTW"  # 換成您的 Hugging Face API token
+
+tokenizer = BertTokenizer.from_pretrained(model_name_or_path, use_auth_token=auth_token)
+model = BertForMaskedLM.from_pretrained(model_name_or_path, use_auth_token=auth_token)
+
+
+def ai_text(text):
+    with torch.no_grad():
+        outputs = model(**tokenizer([text], padding=True, return_tensors='pt'))
+
+    def to_highlight(corrected_sent, errs):
+        output = [{"entity": "糾錯", "word": err[1], "start": err[2], "end": err[3]} for i, err in
+                  enumerate(errs)]
+        return {"text": corrected_sent, "entities": output}
+
+    def get_errors(corrected_text, origin_text):
+        sub_details = []
+        for i, ori_char in enumerate(origin_text):
+            if ori_char in [' ', '“', '”', '‘', '’', '琊', '\n', '…', '—', '擤']:
+                # add unk word
+                corrected_text = corrected_text[:i] + ori_char + corrected_text[i:]
+                continue
+            if i >= len(corrected_text):
+                continue
+            if ori_char != corrected_text[i]:
+                if ori_char.lower() == corrected_text[i]:
+                    # pass english upper char
+                    corrected_text = corrected_text[:i] + ori_char + corrected_text[i + 1:]
+                    continue
+                sub_details.append((ori_char, corrected_text[i], i, i + 1))
+        sub_details = sorted(sub_details, key=operator.itemgetter(2))
+        return corrected_text, sub_details
+
+    _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)
+    print(text, ' => ', corrected_text, details)
+    return corrected_text + ' ' + str(details)
+
+
+if __name__ == '__main__':
+
+examples = [
+    ['你究輸入利的手機門號跟生分證就可以了。'],
+    ['這裡是客服中新，很高性為您服物，請問金天有什麼須要幫忙'],
+    ['因為我們這邊是按天術比例計蒜給您的，其實不會有態大的穎響。也就是您用前面的資非的廢率來做計算'],
+    ['我來看以下，他的時價是多少？起實您就可以直皆就不用到門事'],
+    ['因為你現在月富是六九九嘛，我幫擬減衣百塊，兒且也不會江速'],
+]
+
+    inputs=[gr.Textbox(lines=2, label="欲校正的文字")],
+    outputs=[gr.Textbox(lines=2, label="修正後的文字")],
+    gr.Interface(
+        inputs='text',
+        outputs='text',
+    title="客服ASR文本AI糾錯系統",
+    description="""
+    <a href="https://www.twman.org" target='_blank'>TonTon Huang Ph.D. @ 2024/04 </a><br>
+    輸入ASR文本，糾正同音字/詞錯誤<br>
+    Masked Language Model (MLM) as correction BERT  
+    """,    examples=examples
+    ).launch()