Developed by this Project
An Automatic Speech Recognition model is a tool that can be trained on audio data to transcribe it to text. This helps to speed up the process of writing down what is being said in audio recordings. After being put through the model, the transcript files are reviewed by our team to correct mistakes, then used to retrain the model. To access the ASR model coded and trained by Connor Bechler and use it for your own transcriptions go to: https://huggingface.co/cbechler2/whisper-small-pdc
Additional Resources
- For an online Pennsylvania Dutch dictionary: padutchdictionary.com
- For Pennsylvania Dutch Wordle: https://www.padutchdictionary.com/wattli/
- For another website dedicated to the documentation of the Pennsylvania Dutch language: padutch.net
- For a Pennsylvania Dutch translation corpus: https://www.deitsch.eu/
- To learn Pennsylvania Dutch, consult the following sites and resources:
- Textbooks for learning and teaching Pennsylvania Dutch:
- Using the English-based writing system: https://learn-dutch.org/wp-content/uploads/2022/01/Vella-Bessah-Deitsh-Shvetza.pdf
- Using the German-based system: https://www.amazon.com/Speaking-Amish-Lillian-Daniel-Stoltzfus/dp/1601263724
- Using the German-based system: https://www.amazon.com/Schwetz-Deitsch-Introductory-Pennsylvania-Course/dp/1601265352
- The Pennsylvania German Cultural Heritage Center: https://www.pagerman.org/
- An oral history project on an ex-Amish community in Libby, Montana: https://www.heritageintranslation.org/
- An automatic translator from ChatGPT: https://chatgpt.com/g/g-KahkfdHm0-pennsylvania-dutch-translator
- Software for transcribing spoken language: ELAN (Version 7.1) [Computer software]. (2026). Nijmegen: Max Planck Institute for Psycholinguistics. Retrieved from https://archive.mpi.nl/tla/elan
