Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,14 @@ tags:
|
|
5 |
model-index:
|
6 |
- name: mariav/helsinki-opus-de-en-fine-tuned-wmt16
|
7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
@@ -12,7 +20,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# mariav/helsinki-opus-de-en-fine-tuned-wmt16
|
14 |
|
15 |
-
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-de-en](https://huggingface.co/Helsinki-NLP/opus-mt-de-en) on
|
16 |
It achieves the following results on the evaluation set:
|
17 |
- Train Loss: 1.0077
|
18 |
- Validation Loss: 1.4381
|
@@ -20,15 +28,18 @@ It achieves the following results on the evaluation set:
|
|
20 |
|
21 |
## Model description
|
22 |
|
23 |
-
|
24 |
|
25 |
## Intended uses & limitations
|
26 |
|
27 |
-
|
28 |
|
29 |
## Training and evaluation data
|
30 |
|
31 |
-
|
|
|
|
|
|
|
32 |
|
33 |
## Training procedure
|
34 |
|
@@ -54,4 +65,4 @@ The following hyperparameters were used during training:
|
|
54 |
- Transformers 4.27.4
|
55 |
- TensorFlow 2.12.0
|
56 |
- Datasets 2.11.0
|
57 |
-
- Tokenizers 0.13.2
|
|
|
5 |
model-index:
|
6 |
- name: mariav/helsinki-opus-de-en-fine-tuned-wmt16
|
7 |
results: []
|
8 |
+
datasets:
|
9 |
+
- wmt16
|
10 |
+
language:
|
11 |
+
- de
|
12 |
+
- en
|
13 |
+
metrics:
|
14 |
+
- bleu
|
15 |
+
pipeline_tag: translation
|
16 |
---
|
17 |
|
18 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
|
20 |
|
21 |
# mariav/helsinki-opus-de-en-fine-tuned-wmt16
|
22 |
|
23 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-de-en](https://huggingface.co/Helsinki-NLP/opus-mt-de-en) on the wmt16.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Train Loss: 1.0077
|
26 |
- Validation Loss: 1.4381
|
|
|
28 |
|
29 |
## Model description
|
30 |
|
31 |
+
This model is a fine-tuned version of Helsinki-NLP/opus-mt-de-en with the dataset wmt16 for the pair of languages german-english.
|
32 |
|
33 |
## Intended uses & limitations
|
34 |
|
35 |
+
Limitations: scholar use.
|
36 |
|
37 |
## Training and evaluation data
|
38 |
|
39 |
+
Training done with keras from Transformers.
|
40 |
+
Evaluation with Bleu:
|
41 |
+
|
42 |
+
- Result:
|
43 |
|
44 |
## Training procedure
|
45 |
|
|
|
65 |
- Transformers 4.27.4
|
66 |
- TensorFlow 2.12.0
|
67 |
- Datasets 2.11.0
|
68 |
+
- Tokenizers 0.13.2
|