Multi-task automatic speech recognition system
AssigneeOpenAI OpCo, LLC
InventorsAlec RADFORD, Jong Wook KIM, Tao XU, Greg BROCKMAN, Christine MCLEAVEY-PAYNE, Ilya SUTSKEVER
Life of this patent
Estimating the term…
Loading patent…
AssigneeOpenAI OpCo, LLC
InventorsAlec RADFORD, Jong Wook KIM, Tao XU, Greg BROCKMAN, Christine MCLEAVEY-PAYNE, Ilya SUTSKEVER
Estimating the term…
Disclosed herein are methods, systems, and computer-readable media for generating an output transcript from an input audio segment using a multi-task transformer model. In some embodiments, the transformer model can be trained to transcribe or translate audio data in multiple languages using labeled audio data. The labeled audio data can include first audio segments associated with first same-language transcripts of the first audio segments and second audio segments associated with second different-language transcripts of the second audio segments. In some embodiments, a vocabulary of the model can include special purpose and time stamp tokens. The special purpose tokens can specify tasks for the model to perform.
A system comprising:
A method for multi-language, multi-task speech recognition, comprising:
A non-transitory computer-readable medium including instructions that are executable by one or more processors to perform operations comprising:
Dependencies are inferred from the claim text.