bhavitvyamalik
commited on
Commit
•
f656e2c
1
Parent(s):
07e2406
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- translation
|
4 |
+
license: cc0-1.0
|
5 |
+
---
|
6 |
+
|
7 |
+
### en-mt HPLT v1.0
|
8 |
+
|
9 |
+
Note: This repository only contains the model weights. 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.
|
10 |
+
|
11 |
+
* source language: en
|
12 |
+
* target language: mt
|
13 |
+
* dataset: OPUS + HPLTDatasets v1.2
|
14 |
+
* model: transformer-base
|
15 |
+
* tokenizer: SentencePiece (Unigram)
|
16 |
+
* 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-mt/raw/v2)
|
17 |
+
|
18 |
+
|
19 |
+
## Benchmarks
|
20 |
+
|
21 |
+
| testset | BLEU | chr-F | comet |
|
22 |
+
| -------------------------------------- | ---- | ----- | ----- |
|
23 |
+
| flores200.en.mt | 47.5 | 0.64 | 0.64 |
|
24 |
+
| ntrex.en.mt | 25 | 0.62 | 0.62 |
|