This week’s episode of the NLP Stream featured a project that leverages speech recognition and natural language processing to convert audio files into structured data. Samuel Algherini, technical trainer for expert.ai, showed us how he used a blend of open source and free-to-use AI models and technologies from Facebook AI, Hugging Face, and expert.ai to convert speech into knowledge.
If you would like to learn more, please read Samuel’s article about this project or take a look at his Github repo.
- How to get reports from audio files using speech recognition and NLP | Community (expert.ai)
- Github repo
If you missed the stream, watch the recording on demand.