Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,8 @@ language:
|
|
| 5 |
- en
|
| 6 |
datasets:
|
| 7 |
- scoris/en-lt-merged-data
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
# Overview
|
| 10 |
|
|
@@ -15,7 +17,7 @@ For Lithuanian-English translation check another model [scoris/opus-mt-tc-big-lt
|
|
| 15 |
|
| 16 |
Fine-tuned on large merged data set: [scoris/en-lt-merged-data](https://huggingface.co/datasets/scoris/en-lt-merged-data) (5.4 million sentence pairs)
|
| 17 |
|
| 18 |
-
Trained on
|
| 19 |
|
| 20 |
Made by [Scoris](https://scoris.lt) team
|
| 21 |
|
|
@@ -24,7 +26,7 @@ Tested on scoris/en-lt-merged-data validation set. Metric: sacrebleu
|
|
| 24 |
|
| 25 |
| model | testset | BLEU | Gen Len |
|
| 26 |
|----------|---------|-------|-------|
|
| 27 |
-
| scoris/opus-mt-tc-big-en-lt-scoris-finetuned | scoris/en-lt-merged-data (validation) | 41.
|
| 28 |
| Helsinki-NLP/opus-mt-tc-big-en-lt | scoris/en-lt-merged-data (validation) | 34.2768 | 17.6664
|
| 29 |
|
| 30 |
According to [Google](https://cloud.google.com/translate/automl/docs/evaluate) BLEU score interpretation is following:
|
|
|
|
| 5 |
- en
|
| 6 |
datasets:
|
| 7 |
- scoris/en-lt-merged-data
|
| 8 |
+
metrics:
|
| 9 |
+
- sacrebleu
|
| 10 |
---
|
| 11 |
# Overview
|
| 12 |
|
|
|
|
| 17 |
|
| 18 |
Fine-tuned on large merged data set: [scoris/en-lt-merged-data](https://huggingface.co/datasets/scoris/en-lt-merged-data) (5.4 million sentence pairs)
|
| 19 |
|
| 20 |
+
Trained on 6 epochs.
|
| 21 |
|
| 22 |
Made by [Scoris](https://scoris.lt) team
|
| 23 |
|
|
|
|
| 26 |
|
| 27 |
| model | testset | BLEU | Gen Len |
|
| 28 |
|----------|---------|-------|-------|
|
| 29 |
+
| scoris/opus-mt-tc-big-en-lt-scoris-finetuned | scoris/en-lt-merged-data (validation) | 41.8841 | 17.4785
|
| 30 |
| Helsinki-NLP/opus-mt-tc-big-en-lt | scoris/en-lt-merged-data (validation) | 34.2768 | 17.6664
|
| 31 |
|
| 32 |
According to [Google](https://cloud.google.com/translate/automl/docs/evaluate) BLEU score interpretation is following:
|