Watch On:
Summary
OpenAI’s tests on Whisper show promising results in transcribing audio not only in English, but also in several other languages. Developers and researchers who have experimented with Whisper are also impressed with what the model can do. GPT-3 and DALL-E, two of OpenAI’s most impressive deep learning models, are only available behind paid API services, and there is no way to download and examine them. In contrast, Whisper was released as a pretrained, open-source model that everyone can download and run on a computing platform of their choice. This latest development comes as the past few months have seen a trend toward more openness among commercial AI research labs. Since it is free and programmable, it most likely means a very significant challenge to services that only offer transcribing.” Another interesting direction could be to fine-tune the model for other tasks than ASR, such as speaker verification, sound event detection and keyword spotting. For very technical verticals, a fine-tuned version could be a game changer in how they are able to communicate technical information. “We have already received feedback that you can use Whisper as a plug-and-play service to achieve better results than before,” Philipp Schmid, technical lead at Hugging Face, told VentureBeat. “
Show Notes
Last week, OpenAI released Whisper, an open-source deep learning model for speech recognition.
In contrast, Whisper was released as a pretrained, open-source model that everyone can download and run on a computing platform of their choice.
OpenAI’s Whisper embraces data diversityOne of the important characteristics of Whisper is the diversity of data used to train it.
— Peter Sterne (@petersterne) September 22, 2022Meanwhile, open-source models like Whisper open new possibilities in the cloud.
Or fine-tune existing applications for your purposesAnd another benefit of open-source models like Whisper is fine-tuning — the process of taking a pretrained model and optimizing it for a new application.
Source
https://venturebeat.com/ai/how-will-openais-whisper-model-impact-ai-applications/
