OpenAI has introduced Whisper, an open-source automatic speech recognition system that, according to the company, enables “robust” transcription in multiple languages and translation of those languages into English.
Large tech companies’ software and services are built around highly effective speech recognition systems, which have been developed by countless organizations. Whisper was reportedly trained on 680,000 hours of multilingual and “multitask” data that was gathered from the web, according to OpenAI. This led to improved recognition of distinctive accents, background noise, and technical jargon. Whisper’s debut does not necessarily portend what OpenAI has in store for the future.
While concentrating more on commercial projects like DALL-E 2 and GPT-3, the company is also working on a number of purely theoretical research lines, such as artificial intelligence systems that learn from watching videos.
Read More: OpenAI open-sources Whisper, a multilingual speech recognition system
The Enterprise talk Bureau has five well-trained writers and journalists, well versed in B2B enterprise technology industry, and constantly in touch with industry leaders for the latest trends, opinions, and other inputs- to bring you the best and latest in the domain.
