speech to text
Converting spoken audio into text, often with a timestamp for each word.
In more detail
Transcription error rates rise with noise, accents and jargon. Word timestamps let you build captions and align a transcript with a script to find skipped or misheard words.
Related terms
- text to speech — Generating spoken audio from text with a voice model.
- sequence alignment — Lining up two sequences, such as a script and a transcript, to find the matching runs and the gaps between them.
- multimodal model — A model that accepts or produces more than one kind of data, such as text, images and audio.
Taught in
- Memory And Compaction — AI Engineering: LLM Apps, RAG & Agents
- Model-Graded Evals — AI Engineering: LLM Apps, RAG & Agents
- Evaluating RAG And Agents — AI Engineering: LLM Apps, RAG & Agents
- Tracing And Monitoring — AI Engineering: LLM Apps, RAG & Agents
- Images, Audio And Speech — AI Engineering: LLM Apps, RAG & Agents