Text2Text Generation
Transformers
PyTorch
Estonian
marian
GEC
Grammatical Error Correction
Eval Results
Inference Endpoints
paulpall's picture
Update README.md
758a33d verified
metadata
license: apache-2.0
language:
  - et
metrics:
  - GLEU
  - MaxMatch
pipeline_tag: text2text-generation
base_model: Helsinki-NLP/opus-mt-fi-et
tags:
  - GEC
  - Grammatical Error Correction
widget:
  - text: Dere dere vana gere
    example_title: Grammatical Error Correction
library_name: transformers
model-index:
  - name: GEC_Estonian_OPUS-MT
    results:
      - task:
          type: grammatical-error-correction
        dataset:
          name: Tallinn-L2
          type: Tallinn-L2
        metrics:
          - name: GLEU Reimplementation by Shota Koyama
            type: GLEU
            value: 23.96
            args:
              max_order: 4
          - name: Estonian M2 Scorer by Krista Liin
            type: MaxMatch
            value: 30.1273
co2_eq_emissions:
  emissions: 587.6
  source: >-
    https://arxiv.org/abs/1910.09700, https://carbonintensity.org.uk/,
    https://www.amd.com/en/support/downloads/drivers.html/processors/epyc/epyc-7002-series/amd-epyc-7702.html
  training_type: fine-tuning
  geographical_location: London, United Kingdom
  hardware_used: 1 AMD EPYC 7702 CPU
datasets:
  - paulpall/textbooks-sentences_estonian
  - paulpall/legalese-sentences_estonian