[–] rfv6723 1y ago ↗ Why no comparition to gpt-4o-transcribe？If you don't compare to latest model on the market, how can you claim it's SOTA?According to OpenAI, gpt-4o-transcribe has much better performance than whisper-large-v2.https://openai.com/index/introducing-our-next-generation-aud...
[–] 1317 1y ago ↗ SOTA: not used in the article but probably State Of The ArtASR: Automatic Speech Recognition, speech-to-text [–] lenerdenator 1y ago ↗ And here I was, as a ham radio operator, excited to read something about Summits On The Air.shuffles dejectedly back to shack
[–] lenerdenator 1y ago ↗ And here I was, as a ham radio operator, excited to read something about Summits On The Air.shuffles dejectedly back to shack
[–] albertzeyer 1y ago ↗ Are there any details on what they changed to improve over other existing models?
4 comments
[ 3.7 ms ] story [ 19.9 ms ] threadIf you don't compare to latest model on the market, how can you claim it's SOTA?
According to OpenAI, gpt-4o-transcribe has much better performance than whisper-large-v2.
https://openai.com/index/introducing-our-next-generation-aud...
ASR: Automatic Speech Recognition, speech-to-text
shuffles dejectedly back to shack