- from tools import documents_extractor
- from transcript_extractor import rectify_transcript
- transcript = "E:\\project\\arbitration_system\\transcript_extractor\\test\\庭审笔录.PDF"
- def transcript_extractor_run(transcript):
- reader = documents_extractor.DocumentReader()
- result_reader = reader.process_input(transcript)
- print(result_reader)
- rectify_client = rectify_transcript.RectifyClient_transcript()
- result_rectify = rectify_client.clean_text(result_reader)
- return result_rectify
- print(transcript_extractor_run(transcript))
|
