ENGLISH_ASR / replaceWords.py
cdactvm's picture
Upload 6 files
3b58a97 verified
raw
history blame
3.33 kB
#!/usr/bin/env python
# coding: utf-8
# In[7]:
import re
def replace_words(sentence):
# Define a dictionary mapping a single word to a list of words or phrases
replacement_map = {
# Multiples of ten
'twenty': [],
'thirty': [],
'forty': [],
'fifty': [],
'sixty': [],
'seventy': [],
'eighty': [],
'ninety': [],
# Numbers from 11 to 19
'eleven': [],
'twelve': [],
'thirteen': [],
'fourteen': [],
'fifteen': [],
'sixteen': [],
'seventeen': [],
'eighteen': [],
'nineteen': [],
# Numbers from 21 to 29
'twenty one': [],
'twenty two': [],
'twenty three': [],
'twenty four': [],
'twenty five': [],
'twenty six': [],
'twenty seven': [],
'twenty eight': [],
'twenty nine': [],
# Numbers from 31 to 39
'thirty one': [],
'thirty two': [],
'thirty three': [],
'thirty four': [],
'thirty five': [],
'thirty six': [],
'thirty seven': [],
'thirty eight': [],
'thirty nine': [],
# Numbers from 41 to 49
'forty one': [],
'forty two': [],
'forty three': [],
'forty four': [],
'forty five': [],
'forty six': [],
'forty seven': [],
'forty eight': [],
'forty nine': [],
# Numbers from 51 to 59
'fifty one': [],
'fifty two': [],
'fifty three': [],
'fifty four': [],
'fifty five': [],
'fifty six': [],
'fifty seven': [],
'fifty eight': [],
'fifty nine': [],
# Numbers from 61 to 69
'sixty one': [],
'sixty two': [],
'sixty three': [],
'sixty four': [],
'sixty five': [],
'sixty six': [],
'sixty seven': [],
'sixty eight': [],
'sixty nine': [],
# Numbers from 71 to 79
'seventy one': [],
'seventy two': [],
'seventy three': [],
'seventy four': [],
'seventy five': [],
'seventy six': [],
'seventy seven': [],
'seventy eight': [],
'seventy nine': [],
# Numbers from 81 to 89
'eighty one': [],
'eighty two': [],
'eighty three': [],
'eighty four': [],
'eighty five': [],
'eighty six': [],
'eighty seven': [],
'eighty eight': [],
'eighty nine': [],
# Numbers from 91 to 99
'ninety one': [],
'ninety two': [],
'ninety three': [],
'ninety four': [],
'ninety five': [],
'ninety six': [],
'ninety seven': [],
'ninety eight': [],
'ninety nine': [],
# Numbers from one to ten
'seven': [],
'zero': [],
'one': [],
'two': [],
'three': [],
'four': [],
'five': [],
'six': [],
'eight': [],
'nine': [],
'ten': [],
# Hundred
'hundred': [],
# Thousand
'thousand' : [],
# Lakhs
'lakh' : ['lac','lach','laq','lak'],
}
words = sentence.split() # Split the sentence by spaces
# Replace words using the mapping
for i, word in enumerate(words):
for replacement, patterns in replacement_map.items():
if word in patterns:
words[i] = replacement # Replace the word if it's fully matched
# Join the processed words back into a sentence
return ' '.join(words)
# In[ ]: