-
Hello! Sorry for the basic question.
I've been looking for the breakdown for size of NLLB-200 training data and couldn't found it.
The paper states that NLLB-200 was trained using 3.6B sentences f…
-
## 🐛 Bug
### Try to finetune NLLB but got an error
`Can't instantiate abstract class TrainModule with abstract methods requirements`
### CMD
```
python /fairseq-nllb/examples/nllb…
-
The issue requires a finetunig script and evaluation script for NLLB.
Script should take in CLI arguments and should be uses to run a baseline experiment on the Mafand dataset for 3 epoch. Please l…
owos updated
10 months ago
-
Hello,
I'm working on low resource language translation. Can anyone please provide me the code/notebook of NLLB finetuning? It would be much helpful.
-
I try to use optimum convert nllb to onnx, but get error
```
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Deserialize tensor onnx::MatMul_3635 failed.tensorproto…
-
Hello, I am experiencing some issues while generating subtitles for the video attached below. Despite trying various values in the Advanced Parameters and Voice Detection sections, I am not able to ac…
-
https://huggingface.co/Xenova/nllb-200-distilled-600M
云翻译虽然被调教得好，但就在这网络请求和 API key 就挺烦人的.
离线翻译才是王道。
https://github.com/xenova/transformers.js/blob/da2688626d7812ad1ea47fd304c2072cc685051b/exa…
-
In #771 I tested the effects of reducing the distillation data to understand that expensive part of our pipeline. However, we should do it again for the `base` student model, as the other one was done…
-
This would be for SIL Converters
-
## 🐛 Bug
I'm trying to open and investigate NLLB MoE model (405GB), but can't load it into torch.
Smaller dense models seem to load fine, can access the checkpoint's parameters etc.
### To Repr…