OpenAI releases Whisper
OpenAI released and open-sourced Whisper, an automatic speech recognition model for multilingual transcription, language identification, and speech translation into English.
What happened
Event details
OpenAI released Whisper on September 21, 2022. Trained on 680,000 hours of multilingual and multitask supervised data, the encoder-decoder Transformer performs multilingual transcription, language identification, and translation of non-English speech into English. OpenAI also released the model weights and inference code.
Assessment
Why it matters
Whisper made multilingual speech recognition and translation available for local deployment and became a widely used foundation for open speech-processing tools.
Availability
Access notes
The model weights and inference code are publicly available for local use.