Secure and scalable speech transcription for local and HPC

Wed, 12 Nov 2025 00:00:00 +0000

How it works

graph TD A["Audio input"] --> B["Audio enhancement pipeline"] B --> C["Local Whisper transcription
with GPU acceleration"] C --> D["Remove AI-generated
repetitions"] C --> E["Context-aware name masking"] C --> F["Speaker diarisation"] D --> G["Reproducible and
GDPR-compliant transcript"] E --> G F --> G C --> H["Batch operations
on HPC clusters"]

Reference

If you use this workflow in your research, please cite:

Bernabeu, P. (2025). Secure and scalable speech transcription for local and HPC (Version 1.0.0) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.17624830

The recommended BibTeX entry is:

@misc{secure_local_HPC_speech_transcription,
author = {Bernabeu, Pablo},
title = {Secure and scalable speech transcription for local and {HPC}},
year = {2025},
publisher = {Zenodo},
version = {1.0.0},
doi = {10.5281/zenodo.17624830},
url = {https://doi.org/10.5281/zenodo.17624830}
}

Podcast

Created using NotebookLM, with all the benefits and blind spots of human editing.

9 | Pablo Bernabeu

Secure and scalable speech transcription for local and HPC

How it works

Reference

Podcast