Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nshm
on Dec 6, 2022
|
parent
|
context
|
favorite
| on:
OpenAI quietly launched Whisper V2 in a GitHub com...
Looks like they plugged GPT-4 AI into speech recognition research and now they are going to release huge updates every month.
dweekly
on Dec 6, 2022
[–]
What is the basis for this claim? How does their GPT-4 work intersect with the work on their ASR model?
wcoenen
on Dec 6, 2022
|
parent
|
next
[–]
It's a joke... They're saying GPT-4 is doing the research now.
nshm
on Dec 6, 2022
|
parent
|
prev
[–]
Easily, you can ask questions about speech recognition system design. For example you can ask ChatGPT about upsampling vs downsampling, it gives correct answer. It also can correctly recommend you architecture for streaming speech recognition.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
