-
https://github.com/balisujohn/tortoise.cpp is what we're about to use.
Is there anything better? Report as comment in this issue.
-
Please note our paper on evaluation, which could be an important building block for multilingual evaluation and cultural understanding.
[SeaEval for Multilingual Foundation Models: From Cross-Lingu…
-
- https://arxiv.org/abs/2104.14830
- 2021 INTERSPEECH
多くの言語ファミリーでASR (automatic speech recognition)モデルを構築することは、大きな言語バリエーションと大きく不均衡なデータのため、マルチタスク学習の難しい問題です。
既存の研究では、高リソース言語から低リソース言語へのポジティブな移行が示されて…
e4exp updated
3 years ago
-
Most providers allow the user to indicate which language should be used (instead of relying on the model to identify it). FasterWhisper's transcribe(), for example, allows for an optional "language" p…
-
Hello, for your SBERT models, distilbert-multilingual-nli-stsb-quora-ranking, distiluse-base-multilingual-cased-v2, and xlm-r-100langs-bert-base-nli-stsb-mean-tokens, what's the teacher model and what…
-
Add datasets not yet in MTEB from https://github.com/sdadas/pirb! Would be cool to support this as a benchmark too.
cc @rafalposwiata maybe you know which ones are still missing here? Amazing work on…
-
It would be nice, for us non-English people, to have access to the some good multilanguage/multilingual LLMs.
Bloom comes to mind, but other would be very useful.
https://huggingface.co/blog/bloom
-
Multilingual is "must have" feature for prod deployment for most international companies , any plan to support it for modules ?
For example , perspective api supports multilingual
https://develope…
-
hi there
the M2M 100 readme mentions that the 1.2B parameter model was trained with fairseq's multilingual translation task, without further elaboration. I'm wondering if there could be a example t…
-
I tested the speed of lama models using exlama and noticed that the speed of 8b models is much slower than 7b (although this is not the case with other inferences. Can you tell me what the problem mig…