We also release our robust model and multi-domain evaluation benchmark to the research community

Model huggingface.co/badrex/mms-3...

Eval Dataset 🛢️

I wanted to show that you could ask these questions about pretty much any language (including English). But I'm glad you asked these questions because this opinion is very common among NLP practitioners and I'm curious how we should respond

Shoutout to fellow organizers: Aravind Krishnan @a-krishnan.bsky.social, Francesco Paissan @fpaissan.bsky.social, Cem Subakan, Mirco Ravanelli, and Dietrich Klakow

In a different universe:

Why do we publish English only resources?
linguistic findings?❌ weak due to focus on a single language
support model multilinguality? ❌so why this specific morphologically poor language?
Spoken by a large population?❌ why don't work on Mandarin instead?

That's rigth. It is just an NN, only one hidden layer

It depends on what you mean by speech recognition

If you have a broad definition, you could back to 1980s 😁

pubs.aip.org/asa/jasa/art...

I am working on speech translation nowadays, does that count as MT? 😁

Nah I don't like question answering. For answers please see Yoav Goldberg's comment

Not this bit.

But "So far it seems they [LLMs] have been a great toy." is indeed a controversial opinion

Yoav Goldberg answered Zerak's question in his comment (from an NLP practioner's perspective), although LLMs are not just for NLP stuff

Do you seriously mean that or you intentionally wrote a controversial opinion so people come and attack you? 😁

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP - work led by @mariusmosbach.bsky.social, and done in collaboration with Tomás Vergara-Browne and Mor Geva
aclanthology.org/2024.emnlp-m...

Hello there 👋🏼