Loading…
Glossary term
Technology that converts spoken audio into text.
Speech recognition turns spoken audio into text. A model converts the sound to features and predicts the most likely words, using context to resolve similar-sounding ones.
Large models trained on diverse audio now handle accents, noise and many languages.
Transcribe audio with Whisper
import whisper
model = whisper.load_model("base")
result = model.transcribe("meeting.mp3")
print(result["text"])It underlies voice assistants, captions, dictation and meeting transcripts.