Upload README.md with huggingface_hub

README.md

@@ -16,7 +16,7 @@ This repository contains the model weights for translation models trained with M
 * Dataset: HPLT only
 * 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/ar-en/raw/v0) 
+* 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-ar/raw/v0) 
 
 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.
 
@@ -25,5 +25,5 @@ To run inference with Marian, refer to the [Inference/Decoding/Translation](http
 
 | testset                                | BLEU | chr-F | comet |
 | -------------------------------------- | ---- | ----- | ----- |
-| flores200     | 35.0 | 58.5  | 0.8833  |
-| ntrex | 28.6   | 54.6  | 0.8704  |
+| flores200     | 35.0 | 58.5  | 0.8396  |
+| ntrex | 28.6   | 54.6  | 0.8194  |