# Cross-lingual Pretraining

Sentiment analysis model optimized for Khmer financial texts, capable of classifying positive/negative sentiments

ERNIE-Code is a unified large language model connecting 116 natural languages and 6 programming languages, supporting various cross-lingual tasks.

An image segmentation model based on the Transformers library, supporting various image segmentation tasks.

A Luxembourgish speech recognition model fine-tuned from the wav2vec 2.0 large XLSR-53 checkpoint, trained with 842 hours of unlabeled and 14 hours of labeled data, integrated with a 5-gram language model

XLSR-Wav2Vec2 is a multilingual speech recognition model that learns shared speech representations through cross-lingual pretraining, supporting 53 languages.

A multilingual pretrained model for Chinese and 7 minority languages in China

The XLM model is a bilingual English-French Transformer model pre-trained with causal language modeling objectives, proposed by Guillaume Lample and Alexis Conneau.

XLM-mlm-ende-1024 is an English-German Transformer model pre-trained with the Masked Language Modeling (MLM) objective, using language embeddings to specify the inference language.

A T5 model pre-trained on Korean and English, supporting cross-lingual knowledge-driven response generation

English-German bilingual Transformer model pretrained with causal language modeling objective

XLM is a masked language model trained on English text, using BERT-style MLM objectives for pretraining, supporting English language processing tasks.

An English-Romanian Transformer model pretrained with masked language modeling objective, using language embeddings to specify inference language

XLM-mlm-enfr-1024 is a Transformer model pre-trained on English-French masked language modeling objectives, supporting cross-lingual tasks.