About easytranscriber

easytranscriber was developed by Faton Rekathati at KBLab. KBLab is a national research infrastructure for digital research and development of artificial intelligence at the National Library of Sweden.

License

easytranscriber is licensed under the MIT License.

Acknowledgements

easytranscriber draws heavy inspiration from WhisperX (Bain et al., 2023).

The forced alignment component is based on Pytorch’s forced alignment API, which implements a GPU-accelerated version of the Viterbi algorithm as described in Pratap et al., 2024.

LibriVox audiobooks in the public domain are used as examples in the easytranscriber tutorials.