Upload 2 files
Browse files- khmer_name_tokenizer.model +3 -0
- khmer_name_tokenizer.vocab +54 -0
khmer_name_tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46fed7096e939f717c48aab830ab06ab9a41e8314deb0cdd179a09e691ad5edc
|
3 |
+
size 238311
|
khmer_name_tokenizer.vocab
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<pad> 0
|
2 |
+
<unk> 0
|
3 |
+
<s> 0
|
4 |
+
</s> 0
|
5 |
+
▁ -1.68951
|
6 |
+
ស -2.4669
|
7 |
+
ា -2.48779
|
8 |
+
ន -2.7806
|
9 |
+
ុ -2.92136
|
10 |
+
្ -3.21322
|
11 |
+
រ -3.34003
|
12 |
+
ណ -3.4898
|
13 |
+
ង -3.57042
|
14 |
+
ត -3.65276
|
15 |
+
វ -3.65383
|
16 |
+
េ -3.74914
|
17 |
+
ប -3.87965
|
18 |
+
ី -3.88863
|
19 |
+
៉ -3.91097
|
20 |
+
ម -3.96886
|
21 |
+
អ -3.99009
|
22 |
+
ល -4.01127
|
23 |
+
ិ -4.12505
|
24 |
+
៊ -4.1325
|
25 |
+
ឿ -4.21398
|
26 |
+
ខ -4.47336
|
27 |
+
ភ -4.50292
|
28 |
+
ឹ -4.65277
|
29 |
+
ជ -4.66348
|
30 |
+
គ -4.69428
|
31 |
+
ផ -4.72294
|
32 |
+
ំ -4.75352
|
33 |
+
័ -4.98634
|
34 |
+
ូ -4.99312
|
35 |
+
ក -4.99995
|
36 |
+
ញ -5.01931
|
37 |
+
ៀ -5.29957
|
38 |
+
ធ -5.3126
|
39 |
+
ហ -5.31447
|
40 |
+
ដ -5.31823
|
41 |
+
ៅ -5.37639
|
42 |
+
ព -5.38239
|
43 |
+
ឆ -5.38843
|
44 |
+
់ -5.41505
|
45 |
+
ួ -5.41713
|
46 |
+
ៃ -5.98352
|
47 |
+
ទ -5.99087
|
48 |
+
ឋ -6.02847
|
49 |
+
ច -6.03231
|
50 |
+
ឈ -6.05566
|
51 |
+
ែ -6.0836
|
52 |
+
ឧ -6.14626
|
53 |
+
ោ -6.15058
|
54 |
+
ថ -6.19032
|