File tree 2 files changed +39
-9
lines changed
2 files changed +39
-9
lines changed Original file line number Diff line number Diff line change 2
2
"cells" : [
3
3
{
4
4
"cell_type" : " code" ,
5
- "execution_count" : 3 ,
5
+ "execution_count" : 1 ,
6
6
"metadata" : {},
7
7
"outputs" : [],
8
8
"source" : [
12
12
},
13
13
{
14
14
"cell_type" : " code" ,
15
- "execution_count" : 4 ,
15
+ "execution_count" : 2 ,
16
16
"metadata" : {},
17
17
"outputs" : [
18
18
{
29
29
},
30
30
{
31
31
"cell_type" : " code" ,
32
- "execution_count" : 5 ,
32
+ "execution_count" : 3 ,
33
33
"metadata" : {},
34
34
"outputs" : [
35
35
{
49
49
]
50
50
},
51
51
"metadata" : {},
52
- "execution_count" : 5
52
+ "execution_count" : 3
53
53
}
54
54
],
55
55
"source" : [
58
58
},
59
59
{
60
60
"cell_type" : " code" ,
61
- "execution_count" : 6 ,
61
+ "execution_count" : 4 ,
62
62
"metadata" : {},
63
63
"outputs" : [
64
+ {
65
+ "output_type" : " display_data" ,
66
+ "data" : {
67
+ "text/plain" : " HBox(children=(FloatProgress(value=0.0, max=47124.0), HTML(value='')))" ,
68
+ "application/vnd.jupyter.widget-view+json" : {
69
+ "version_major" : 2 ,
70
+ "version_minor" : 0 ,
71
+ "model_id" : " a5478389bdef45a9b540ab5820f00d02"
72
+ }
73
+ },
74
+ "metadata" : {}
75
+ },
64
76
{
65
77
"output_type" : " stream" ,
66
- "name" : " stderr" ,
78
+ "name" : " stdout" ,
79
+ "text" : [
80
+ " \n "
81
+ ]
82
+ },
83
+ {
84
+ "output_type" : " display_data" ,
85
+ "data" : {
86
+ "text/plain" : " HBox(children=(FloatProgress(value=0.0, max=8316.0), HTML(value='')))" ,
87
+ "application/vnd.jupyter.widget-view+json" : {
88
+ "version_major" : 2 ,
89
+ "version_minor" : 0 ,
90
+ "model_id" : " c614aa1937ff47549baf3090e416fb5c"
91
+ }
92
+ },
93
+ "metadata" : {}
94
+ },
95
+ {
96
+ "output_type" : " stream" ,
97
+ "name" : " stdout" ,
67
98
"text" : [
68
- " Loading cached processed dataset at /home/zaid/.cache/huggingface/datasets/metrec/plain_text/1.0.0/0aa53fa2a3ad2b8c6301f689d374ca15ee2b410077a2bb35a85766425cd5b435/cache-8b2aa90713d28589.arrow\n " ,
69
- " Loading cached processed dataset at /home/zaid/.cache/huggingface/datasets/metrec/plain_text/1.0.0/0aa53fa2a3ad2b8c6301f689d374ca15ee2b410077a2bb35a85766425cd5b435/cache-2d37aca31a07b63b.arrow\n "
99
+ " \n "
70
100
]
71
101
}
72
102
],
Original file line number Diff line number Diff line change @@ -43,7 +43,7 @@ from datasets import load_dataset
43
43
44
44
dataset = load_dataset(' metrec' )
45
45
46
- cleander = tn.Tnqeeh (remove_diacritics = True )
46
+ cleander = tn.Tnkeeh (remove_diacritics = True )
47
47
cleaned_dataset = cleander.clean_hf_dataset(dataset, ' text' )
48
48
49
49
```
You can’t perform that action at this time.
0 commit comments