My worry is that ASR will end up like OCR. If the multi modal large AI system is good enough (latency wise), the advantage of domain understanding eats the other technlogies alive.
In OCR, even when the characters are poorly scanned, the deep domain understanding these large multi modal AIs have allows it to understand what the document actually meant - this is going to be order id because in the million invoices I have seen before order id is normally below order date - etc. The same issue is going to be there in ASR also is my worry.
topazas 2 minutes ago [-]
How hard could it be to train other European language(-s)?
geooff_ 38 minutes ago [-]
I can't say enough nice things about Cohere's services. I migrated over to their embedding model a few months ago for clip-style embeddings and it's been fantastic.
It has the most crisp, steady P50 of any external service I've used in a long time.
bluegatty 2 minutes ago [-]
can u comment on overall quality? their models tend to be a bit smaller and less performant overall.
simonw 31 minutes ago [-]
It's great that this is Apache 2.0 licensed - several of Cohere's other models are licensed free for non-commercial use only.
Rendered at 17:22:06 GMT+0000 (Coordinated Universal Time) with Vercel.
In OCR, even when the characters are poorly scanned, the deep domain understanding these large multi modal AIs have allows it to understand what the document actually meant - this is going to be order id because in the million invoices I have seen before order id is normally below order date - etc. The same issue is going to be there in ASR also is my worry.
It has the most crisp, steady P50 of any external service I've used in a long time.