Whisper
Whisper is a family of OpenAI automatic speech-recognition models that transcribe and translate spoken audio, including multilingual audio.
Data Analysis with LLMs
whisper-1 is the model identifier for the Whisper speech-transcription model in the OpenAI API.
- How it is used
- Transcribes recorded speech to text and supplies voice input to downstream applications.
- How deep it goes
- Defines Whisper as a multilingual Transformer model and demonstrates its API call, stopping short of explaining model internals.
- Examples
- Uses MP3 recordings, a literary quote, microphone input, and a voice interface that queries an SQLite database.
- What you can do after
- Operate Whisper via OpenAI’s Python library to transcribe supported audio files and feed transcripts into applications.
Build Applications with Local AI Models on a Mac
Whisper is an automatic speech-recognition model developed by OpenAI for transcribing multilingual audio.
- How it is used
- Provides offline speech-to-text input for a voice-enabled chatbot.
- How deep it goes
- Explains the spectrogram-to-encoder-to-decoder flow and gives recording, model-selection, and transcription guidance without detailing model training.
- Examples
- Uses microphone recording, a transcribe() call, and a reusable voice_input.py module.
- What you can do after
- Apply it via MLX Whisper to transcribe recordings and create reusable microphone voice-input functions.
Read how Build Applications with Local AI Models on a Mac explains Whisper →
Related concepts
- encoder-decoder transformerkind of · An encoder-decoder transformer is a neural-network architecture whose encoder processes an input sequence and whose decoder generates an output sequence conditioned on the encoded representation.
- neural networkkind of · A neural network is a computational model of interconnected, parameterized units that learns transformations from inputs to outputs.
- speech recognitionimplements · Speech recognition is the computational conversion of spoken language from audio into a machine-readable representation, typically text.
- MLX Whisperimplemented by · MLX Whisper is a speech-recognition implementation that packages the Whisper model in a format optimized for Apple's MLX framework.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.