David Dale
David Dale
No, I just copy-pasted the code I needed directly into my project without installing the whole urduhack package.
@simplew2011 Could you please try to compress these models yourself, choosing the balance between size and quality which is optimal for you? If you do it, I would be happy...
@starinacool добавите? :)
Hi! > 1. What would be required to fine-tune NLLB for Mi'kmaq? The main requirements are parallel training data and compute. As training data, you need at least thousands or...
> I wonder if there is no current tutorial (maybe from the NLLB community)? @MaxWenzel I could probably write a new one, with updated dependencies and better resistance to catastrophic...
Hi ASMIftekhar! > Based on my understanding Mutox only takes audio files as input and ASR-Mutox takes the whishper generated text transcripts as input Yes, this understanding is correct.
We didn't release the source code for the evaluation. But, if I get the idea right (@mfcoria please correct me if not), we computed all possible precision-recall pairs, (e.g. using...
@ASMIftekhar unfortunately, it is very difficult for us to publish speech data. However, if you extracted the audios from the links that are still alive and published them elsewhere (e.g....
@hackyotter the cell just above this one installs the `seamless_communication` package.
> as a part of https://github.com/embeddings-benchmark/mteb/pull/216 where it was pretty close to a merge but sadly never got finished. Actually, I would be happy to revive #216, but I would...