Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,6 @@
|
|
| 2 |
|
| 3 |
This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we are allowed to distribute the pretrained model.
|
| 4 |
|
| 5 |
-
The pre-training was done using the fairseq library in January 2021.
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we are allowed to distribute the pretrained model.
|
| 4 |
|
| 5 |
+
The pre-training was done using the fairseq library in January 2021.
|
| 6 |
+
|
| 7 |
+
It needs to be fine-tuned in order to perform speech recognition.
|