| #!/usr/bin/env python | |
| # coding: utf-8 | |
| # In[ ]: | |
| # import nbimporter | |
| import nbimporter | |
| from Text2List import text_to_list | |
| def convert_to_list(text, text_list): | |
| matched_words = [] | |
| unmatched_text = '' # To accumulate unmatched characters | |
| # Sort text_list by length in descending order to prioritize longest matches first | |
| text_list_sorted = sorted(text_list, key=len, reverse=True) | |
| while text: | |
| matched = False | |
| for word in text_list_sorted: | |
| if text.startswith(word): | |
| # Add any accumulated unmatched text before appending the matched word | |
| if unmatched_text: | |
| matched_words.append(unmatched_text) | |
| unmatched_text = '' # Reset unmatched text accumulator | |
| matched_words.append(word) | |
| text = text[len(word):] # Remove the matched part from text | |
| matched = True | |
| break | |
| if not matched: | |
| # Accumulate unmatched characters | |
| unmatched_text += text[0] | |
| text = text[1:] | |
| # If there's any remaining unmatched text, add it to the result | |
| if unmatched_text: | |
| matched_words.append(unmatched_text) | |
| # Join matched words and unmatched text with a space | |
| result = ' '.join(matched_words) | |
| return result | |
| # text = "जीरोएकदोतीनचारपांचछहसातआठनौदसजीरोएकदोतीनचारपांच" | |
| if __name__=="__main__": | |
| converted=convert_to_list(text, text_to_list()) | |
| print(converted) | |
| # In[ ]: | |
| # # import nbimporter | |
| # import nbimporter | |
| # from Text2List import text_to_list | |
| # def convert_to_list(text, text_list): | |
| # matched_words = [] | |
| # unmatched_text = '' # To accumulate unmatched characters | |
| # # Sort text_list by length in descending order to prioritize longest matches first | |
| # text_list_sorted = sorted(text_list, key=len, reverse=True) | |
| # while text: | |
| # matched = False | |
| # for word in text_list_sorted: | |
| # if word in text: | |
| # # Add any accumulated unmatched text before appending the matched word | |
| # if unmatched_text: | |
| # matched_words.append(unmatched_text) | |
| # unmatched_text = '' # Reset unmatched text accumulator | |
| # matched_words.append(word) | |
| # text = text[len(word):] # Remove the matched part from text | |
| # matched = True | |
| # break | |
| # if not matched: | |
| # # Accumulate unmatched characters | |
| # unmatched_text += text[0] | |
| # text = text[1:] | |
| # # If there's any remaining unmatched text, add it to the result | |
| # if unmatched_text: | |
| # matched_words.append(unmatched_text) | |
| # # Join matched words and unmatched text with a space | |
| # result = ' '.join(matched_words) | |
| # return result | |
| # text = "जीरोएकदोतीनचार" | |
| # if __name__=="__main__": | |
| # converted=convert_to_list(text, text_to_list()) | |
| # print(converted) | |
| # In[ ]: | |
| get_ipython().system('git clone https://huggingface.co/StephennFernandes/wav2vec2-XLS-R-300m-konkani') | |
| # In[ ]: | |