Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
|
| 11 |
Tested with 1000 samples from the previous datasets Median CER 1.1% MEAN CER 4.2%
|
| 12 |
More detailed info coming later...
|
|
|
|
| 1 |
+
Based on Finnish pretrained T5 model version small-nl24
|
| 2 |
+
|
| 3 |
+
Train data:
|
| 4 |
+
Around 300k samples from from following datasets
|
| 5 |
+
- [wikipedia](https://huggingface.co/datasets/wikipedia)
|
| 6 |
+
- [Yle Finnish News Archive 2011-2018](http://urn.fi/urn:nbn:fi:lb-2017070501)
|
| 7 |
+
- [Yle Finnish News Archive 2019-2020](http://urn.fi/urn:nbn:fi:lb-2021050401)
|
| 8 |
+
- [Finnish News Agency Archive (STT)](http://urn.fi/urn:nbn:fi:lb-2018121001)
|
| 9 |
+
- [The Suomi24 Sentences Corpus](http://urn.fi/urn:nbn:fi:lb-2020021803)
|
| 10 |
|
| 11 |
Tested with 1000 samples from the previous datasets Median CER 1.1% MEAN CER 4.2%
|
| 12 |
More detailed info coming later...
|