arpelarpe commited on
Commit
9120024
1 Parent(s): 4d6e08e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -6,9 +6,10 @@ license: apache-2.0
6
  ---
7
 
8
  # Wav2vec2-base for Danish
9
-
10
  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 were allowed to distribute the pretrained model.
11
 
 
 
12
  The pre-training was done using the fairseq library in January 2021.
13
 
14
  It needs to be fine-tuned to perform speech recognition.
 
6
  ---
7
 
8
  # Wav2vec2-base for Danish
 
9
  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 were allowed to distribute the pretrained model.
10
 
11
+ This model was pretrained on 16kHz sampled speech audio. When using the model, make sure to use speech audio sampled at 16kHz.
12
+
13
  The pre-training was done using the fairseq library in January 2021.
14
 
15
  It needs to be fine-tuned to perform speech recognition.