Upload README.md with huggingface_hub

README.md

@@ -16,14 +16,14 @@ This repository contains the model weights for translation models trained with M
 * Dataset: All of OPUS including HPLT
 * Model: transformer-base
 * Tokenizer: SentencePiece (Unigram)
-* Cleaning: We use OpusCleaner for cleaning the corpus. Details about rules used can be found in the filter files in [Github](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0/data/en-gl/raw/v2) 
+* Cleaning: We use OpusCleaner for cleaning the corpus. Details about rules used can be found in the filter files in [Github](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0/data/gl-en/raw/v2) 
 
 To run inference with Marian, refer to the [Inference/Decoding/Translation](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0#inferencedecodingtranslation) section of our GitHub repository.
 
 
 ## Benchmarks
 
-| testset                                | BLEU | chr-F | comet |
+| testset                                | BLEU | chr-F | COMET-22 |
 | -------------------------------------- | ---- | ----- | ----- |
-| flores200     | 32.5 | 57.5  | 0.8645  |
-| ntrex | 32.7   | 56.8  | 0.834  |
+| flores200     | 32.5 | 57.5  | 0.842  |
+| ntrex | 32.7   | 56.8  | 0.7962  |