Workshop in automatic transcription part 2: Whisper
Part 2 of our workshop series in automated transcription builds on part 1, but if you have previous experience of transcription and/or scripting, you can choose to only sign up for this part. The workshop is mainly aimed at researchers and others who work with anonymized material.
Welcome to a continuation workshop on automatic transcription based on an inventory of needs, wishes and competencies in digital humanities at Linnaeus University.
This time we take on automatic transcription using Whisper through Python. The workshop builds on prior knowledge that you can get by participating in Workshop in automatic transcription part 1: MyGoodTape, and expands the practical use of automatic transcription by introducing new functionality through the use of code. The focus is on using Named Entity Recognition (NER) to mark and hide names of people and places in transcribed text. With the help of NER, you will learn how to automatically transcribe your audio file into an anonymized text.
We will provide a set of example files and tools to prepare your own material for the workshop.
The workshop will be held in the LiLa Lab in Växjö. The number of places is limited and registration is made to Daniel Ocic Ihrmark at email@example.com. If you have any questions about the workshop, Daniel can also answer them. The last day to register is 10 May, 2024.