pinzhenchen commited on
Commit
160356f
1 Parent(s): 56b4343

update README

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  language:
3
- - hi
4
  - en
5
  tags:
6
  - translation
@@ -9,21 +9,21 @@ license: cc-by-4.0
9
 
10
  ### HPLT MT release v1.0
11
 
12
- This repository contains the translation model for hi-en trained with HPLT data only. For usage instructions, evaluation scripts, and inference scripts, please refer to the [HPLT-MT-Models v1.0](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0) GitHub repository.
13
 
14
  ### Model Info
15
 
16
- * Source language: hi
17
- * Target language: en
18
  * Data: HPLT data only
19
  * Model architecture: Transformer-base
20
  * Tokenizer: SentencePiece (Unigram)
21
- * Cleaning: We used OpusCleaner with a set of basic rules. Details can be found in the filter files in [Github](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0/data/en-hi/raw/v0)
22
 
23
  You can also read our deliverable report [here](https://hplt-project.org/HPLT_D5_1___Translation_models_for_select_language_pairs.pdf) for more details.
24
 
25
  ### Usage
26
- *Note* that for quality considerations, we recommend using `[HPLT/translate-hi-en-v1.0-hplt_opus](https://huggingface.co/HPLT/translate-hi-en-v1.0-hplt_opus)` instead of this model.
27
 
28
  The model has been trained with Marian. To run inference, refer to the [Inference/Decoding/Translation](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0#inferencedecodingtranslation) section of our GitHub repository.
29
 
@@ -33,8 +33,8 @@ The model can be used with the Hugging Face framework if the weights are convert
33
 
34
  | testset | BLEU | chrF++ | COMET22 |
35
  | -------------------------------------- | ---- | ----- | ----- |
36
- | flores200 | 35.2 | 59.9 | 0.8741 |
37
- | ntrex | 27.4 | 54.6 | 0.8485 |
38
 
39
  ### Acknowledgements
40
 
 
1
  ---
2
  language:
3
+ - eu
4
  - en
5
  tags:
6
  - translation
 
9
 
10
  ### HPLT MT release v1.0
11
 
12
+ This repository contains the translation model for eu-en trained with HPLT data only. For usage instructions, evaluation scripts, and inference scripts, please refer to the [HPLT-MT-Models v1.0](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0) GitHub repository.
13
 
14
  ### Model Info
15
 
16
+ * Source language: Basque
17
+ * Target language: English
18
  * Data: HPLT data only
19
  * Model architecture: Transformer-base
20
  * Tokenizer: SentencePiece (Unigram)
21
+ * Cleaning: We used OpusCleaner with a set of basic rules. Details can be found in the filter files in [Github](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0/data/en-eu/raw/v0)
22
 
23
  You can also read our deliverable report [here](https://hplt-project.org/HPLT_D5_1___Translation_models_for_select_language_pairs.pdf) for more details.
24
 
25
  ### Usage
26
+ **Note** that for quality considerations, we recommend using [HPLT/translate-eu-en-v1.0-hplt_opus](https://huggingface.co/HPLT/translate-eu-en-v1.0-hplt_opus) instead of this model.
27
 
28
  The model has been trained with Marian. To run inference, refer to the [Inference/Decoding/Translation](https://github.com/hplt-project/HPLT-MT-Models/tree/main/v1.0#inferencedecodingtranslation) section of our GitHub repository.
29
 
 
33
 
34
  | testset | BLEU | chrF++ | COMET22 |
35
  | -------------------------------------- | ---- | ----- | ----- |
36
+ | flores200 | 19.4 | 45.7 | 0.781 |
37
+ | ntrex | 15.7 | 41.4 | 0.743 |
38
 
39
  ### Acknowledgements
40