clr commited on
Commit
49135c4
·
1 Parent(s): b205bca

Upload corpora.py

Browse files
Files changed (1) hide show
  1. corpora.py +9 -0
corpora.py ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ from datasets import load_dataset, Audio
2
+
3
+
4
+ ds_i = load_dataset("language-and-voice-lab/samromur_asr",split='validation')
5
+ ds_i = ds_i.cast_column("audio", Audio(sampling_rate=16_000))
6
+
7
+ ds_f = load_dataset("carlosdanielhernandezmena/ravnursson_asr",split='validation')
8
+ ds_f = ds_f.cast_column("audio", Audio(sampling_rate=16_000))
9
+