|
|
@@ -162,22 +162,6 @@ def fuzzy_correct_chinese(text, correct_terms):
|
|
|
corrected_words.append(word)
|
|
|
return ''.join(corrected_words)
|
|
|
|
|
|
-# def fuzzy_correct_chinese(text, correct_terms):
|
|
|
-# words = jieba.cut(text)
|
|
|
-# corrected_words = []
|
|
|
-# for word in words:
|
|
|
-# if word in error_correction:
|
|
|
-# corrected_words.append(error_correction[word])
|
|
|
-# else:
|
|
|
-# for term in correct_terms:
|
|
|
-# if compare_chinese_words(word, term, tone_sensitive=True):
|
|
|
-# print(f"corrected: {word} -> {term}")
|
|
|
-# corrected_words.append(term)
|
|
|
-# break
|
|
|
-# else:
|
|
|
-# corrected_words.append(word)
|
|
|
-# return ''.join(corrected_words)
|
|
|
-
|
|
|
|
|
|
def post_process_transcript(transcript, temperature=0):
|
|
|
correct_terms = ["溫室氣體", "碳排放", "碳管理", "碳盤查", "碳權交易", "碳費",
|
