ML6 Team

company

• https://ml6.eu/

Research interests

Multilingual Natural Language Processing - Summarization - Entity Extraction - Speech to Text - Text classification

Team members 11

spaces 1

EmojiPredictor

models 10

Recently Updated
Alphabetical

ml6team/mbart-large-cc25-cnn-dailymail-nl-finetune

• Updated 9 days ago • 810 • 7

ml6team/mbart-large-cc25-cnn-dailymail-nl

• Updated Sep 7 • 172 • 6

ml6team/byt5-base-dutch-ocr-correction

Text2Text Generation

• Updated Jul 28 • 241 • 8

ml6team/gpt2-small-german-finetune-oscar

Text Generation

• Updated May 23 • 305 • 6

ml6team/gpt2-small-dutch-finetune-oscar

Text Generation

• Updated May 23 • 16 • 6

ml6team/gpt2-medium-german-finetune-oscar

Text Generation

• Updated May 23 • 48 • 6

ml6team/gpt2-medium-dutch-finetune-oscar

Text Generation

• Updated May 23 • 235 • 6

ml6team/gpt-2-small-conditional-quote-generator

Text Generation

• Updated May 23 • 18 • 6

ml6team/gpt-2-medium-conditional-quote-generator

Text Generation

• Updated May 23 • 211 • 6

ml6team/mt5-small-german-finetune-mlsum

• Updated Jan 28 • 274 • 6

datasets 1

ml6team/cnn_dailymail_nl

This dataset is the CNN/Dailymail dataset translated to Dutch. This is the original dataset: ``` load_dataset("cnn_dailymail", '3.0.0') ``` And this is the HuggingFace translation pipeline: ``` pipeline( task='translation_en_to_nl', model='Helsinki-NLP/opus-mt-en-nl', tokenizer='Helsinki-NL...