fairseq

fairseq copied to clipboard

## 🐛 Bug Hello i have downloaded the many to many mbart50 and i want to test it in en-fr with data from wmt. It did not work and I...

MathieuGrosso

How to convert model trained with QuantNoise to quantized model runnable on CPU only?

3

#### What is your question? I successfully trained a translation model with scalar quantization and I am wondering how to convert the fake INT8 weights to regular INT8 weights? When...

stolam

Data2Vec: error when loading own pretrained model

3

Hi, I'm currently training an own Data2Vec text model with the latest `fairseq` master version. When I'm loading the model checkpoint with: ```bash cd examples/data2vec/models ``` then: ```python from data2vec_text...

stefan-it

No module named 'npy_append_array'

3

Excuse me,can someone answer this quesion? When i run the pyfile,fairseq/examples/hubert/dump_mfcc_feature.py,it will report an error:No module named 'npy_append_array'.And there are no relevant files in the fairseq I downloaded. Please ask...

646312715

Hi, #4513 introduced PyTorch version checks, that are problematic when using NVIDIA PyTorch images. Let's have a look at one code snippet, where the version check is performed: https://github.com/facebookresearch/fairseq/blob/5307a0e078d7460003a86f4e2246d459d4706a1d/fairseq/modules/transformer_layer.py#L118-L138 The...

stefan-it

The use of the ---bpe parameter in fairseq-proprecess

2

We find that the vocabulary obtained with `--bpe` in fairseq-proprecess is the same regardless of being specified as [`character/subword-nmt/fast_bpe` etc.], when we use the following command. ```bash fairseq-preprocess --source-lang mo...

Old-Young233

How to generate my own distillation dataset for Levenshtien Transformer

6

## 🐛 Bug According to the [doc](https://github.com/pytorch/fairseq/tree/master/examples/nonautoregressive_translation#knowledge-distillation), it said "The easiest way of performing distillation is to follow the instructions of training a standard transformer model on the same data,...

Ir1d

OOM to train translation models with very large multilingual dataset.

4

## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the docs. #### What is your question? I try to train a multilingual translation model with...

SefaZeng

[Non-autoregressive Transformer] Add GLAT, CTC, DS

7

This PR adds the code for the following methods to the Non-Autoregressive Transformer: - Glancing Transformer (GLAT) from "[Glancing Transformer for Non-Autoregressive Neural Machine Translation](https://aclanthology.org/2021.acl-long.155.pdf)" (Qian et al., 2021) -...

SirRob1997

How to finetune wmt on your own data

14

Hi! Recently I stumbled across your repo and wmt models. They showed pretty good results on my data out-of-the-box (I uploaded them via HuggingFace) but I failed to find any...

tatiana-iazykova