Skip to main content
The 2024 Developer Survey results are live! See the results

Questions tagged [machine-translation]

Machine Translation, a subfield of Natural Language Processing, is the automatic translation of human languages. While historical translators are based on Statistical Machine Translation, newer systems use Neural Networks which provide much better results.

machine-translation
0 votes
1 answer
59 views

Translating Documents in Azure AI Translator

Can someone please point me to a good, easy-to-understand resource on how to get documents translated within Azure AI Translator? Ideally, a step-by-step instruction video. Thanks! The Azure AI ...
David Jett's user avatar
0 votes
1 answer
42 views

Getting a ValueError on loading a custom keras model

I have made a Custom Keras model for Machine Translation. After saving the model as tf_model.keras , during loading I am getting an error. I have added get_config() and from_config() function and also ...
user8916969's user avatar
0 votes
1 answer
30 views

Why am I getting a TypeError while loading a custom model in keras

I have made a Custom Keras model for Machine Translation. After training and saving the model as tf_model.keras , during loading I am getting an error. I have added get_config() function and also ...
user8916969's user avatar
1 vote
0 answers
25 views

How Can I Optimize Machine Translation Model Training to Overcome GPU Memory Overflow Issues?

I'm trying to train a fairly standard machine translation transformer model using PyTorch. It's based on the "Attention is All You Need" paper. When I ran it on my PC with standard ...
dsb's user avatar
  • 2,477
1 vote
1 answer
38 views

How do I determine the weight? depending on what?

I'm trying to calculate the n--gram using Python. The weight I used for for uni-gram, bi-gram, tri-gram, and 4-gram is (0.25, 0.25, 0, 0). When I run the script for the first reference it gives me a ...
user20003920's user avatar
0 votes
0 answers
41 views

I am implementing transformers from scratch in pytorch and getting some error in addition in positional encoding part in output layer

I am implementing transformer in pytorch and getting an error when the Positional encoding is applied in the decoder layer that is in the op_positional_encoding = self.positional_encoding(op_embed) ...
user8916969's user avatar
0 votes
0 answers
33 views

transformer model predicting the same token during infrence but performing well during training

my transformer model is not working right. Training loop : for epoch in range(40): data_loader = tqdm(data_loader, desc=f"Epoch {epoch + 1}/{20}", unit="batch") for batch_idx, (...
ayush sharma's user avatar
0 votes
0 answers
12 views

Transformer from Scratch can not make inference

I'm coding a Transformer base on this Github link but when the training process was already done, it can only infer the characters and nothing else while testing. I will describe what i had done so ...
MY_NAME_S3M's user avatar
1 vote
0 answers
25 views

How can i make a transformer output a translation relative to a specific context

I am working a machine-translation-like project, where i have a transformer with the encoder-decoder structure, which is supposed to generate SQL queries from natural language commands, example: Input:...
Othman Birem's user avatar
4 votes
1 answer
723 views

How to fine-tune a Mistral-7B model for machine translation?

There's a lot of tutorials online that uses raw text affix with arcane syntax to indicate document boundary and accessed through Huggingface datasets.Dataset object through the text key. E.g. from ...
alvas's user avatar
  • 120k
0 votes
1 answer
67 views

Using MBart50TokenizerFast tokenizer with multiple sentences

I am trying to use MBart50TokenizerFast with facebook/mbart-large-50-many-to-one-mmt on GPU, and trying to provide multiple sentences in one go (the sentences cannot be combined). Here is my code (...
Samik R's user avatar
  • 1,638
1 vote
1 answer
386 views

Huggingface Tokenizer not adding the padding tokens

I am trying to follow this to translate english sentences to japanese. Using this line: import torch from transformers import AutoTokenizer from auto_gptq import AutoGPTQForCausalLM ...
Labyrinthian's user avatar
0 votes
0 answers
47 views

Problem during Custom Sentence Translations with Seq2Seq Transformer Model (English to Spanish)

I am trying to create a translator from English to Spanish based on the Transformer architecture and code mostly taken from the Pytorch Docs. For training I used a Kaggle Dataset. I trained the neural ...
soosmann's user avatar
0 votes
0 answers
153 views

Adding a new language to facebook/m2m100_418M model

I am trying to add a new language to the pretrained M2M model (facebook/m2m100_418M) but I really don't know how to start. Is there anyway that i can add a new language to the model and eliminate ...
Ane Garcia's user avatar
3 votes
4 answers
203 views

Is it possible in HTML5 to give translation service a hint for translating a specific element

I would like a specific element to be translated in a specific way for a specific language pair. For example, a movie-related web page like: <!DOCTYPE html> <html lang="tr"> ... &...
FedKad's user avatar
  • 565

15 30 50 per page
1
2 3 4 5
24