OpenAI: Difference between revisions

[[OpenAI Whisper]] is an open-source [[automatic speech recognition]] (ASR) system that enables transcription in multiple languages and translation into English <ref name="”20”">Wiggers, K (2022). OpenAI open-sources Whisper, a Multilingual Speech Recognition System. TechCrunch. https://techcrunch.com/2022/09/21/openai-open-sources-whisper-a-multilingual-speech-recognition-system/</ref> <ref name="”21”">Bureau, ET (2022). OpenAI Open-Sources Multilingual Speech Recognition System, Dubbed Whisper. EnterpriseTalk. https://enterprisetalk.com/quick-bytes/openai-open-sources-multilingual-speech-recognition-system-dubbed-whisper/</ref> <ref name="”22”">OpenAI (2022). Introducing Whisper. OpenAI. https://openai.com/blog/whisper/</ref>. OpenAI stated that the system has been "trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language <ref name="”22”" />." The primary users of Whisper are intended to be AI researchers "studying robustness, generalization, capabilities, biases and constraints of the current model." Several downloadable versions of Whisper are available at Github and, according to OpenAI, have shown strong ASR results in more or less 10 languages <ref name="”20”" />.