Commit
β’
79f26e3
1
Parent(s):
438f425
Upload tokenizer
Browse files- tokenizer_config.json +0 -3
- vocab.json +35 -35
tokenizer_config.json
CHANGED
@@ -1,12 +1,9 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
-
"clean_up_tokenization_spaces": true,
|
4 |
"do_lower_case": false,
|
5 |
"eos_token": "</s>",
|
6 |
-
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
-
"target_lang": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
"unk_token": "[UNK]",
|
12 |
"word_delimiter_token": "|"
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
|
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
|
|
5 |
"pad_token": "[PAD]",
|
6 |
"replace_word_delimiter_char": " ",
|
|
|
7 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
8 |
"unk_token": "[UNK]",
|
9 |
"word_delimiter_token": "|"
|
vocab.json
CHANGED
@@ -1,39 +1,39 @@
|
|
1 |
{
|
2 |
-
"'":
|
3 |
-
"(":
|
4 |
-
")":
|
5 |
"[PAD]": 36,
|
6 |
"[UNK]": 35,
|
7 |
-
"a":
|
8 |
-
"b":
|
9 |
-
"c":
|
10 |
-
"d":
|
11 |
-
"e":
|
12 |
-
"f":
|
13 |
-
"g":
|
14 |
-
"h":
|
15 |
-
"i":
|
16 |
-
"j":
|
17 |
-
"k":
|
18 |
-
"l":
|
19 |
-
"m":
|
20 |
-
"n":
|
21 |
-
"o":
|
22 |
-
"p":
|
23 |
-
"q":
|
24 |
-
"r":
|
25 |
-
"s":
|
26 |
-
"t":
|
27 |
-
"u":
|
28 |
-
"v":
|
29 |
-
"w":
|
30 |
-
"x":
|
31 |
-
"y":
|
32 |
-
"z":
|
33 |
-
"|":
|
34 |
-
"Γ":
|
35 |
-
"β":
|
36 |
-
"β":
|
37 |
-
"β":
|
38 |
-
"β":
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"'": 22,
|
3 |
+
"(": 32,
|
4 |
+
")": 0,
|
5 |
"[PAD]": 36,
|
6 |
"[UNK]": 35,
|
7 |
+
"a": 13,
|
8 |
+
"b": 23,
|
9 |
+
"c": 4,
|
10 |
+
"d": 18,
|
11 |
+
"e": 8,
|
12 |
+
"f": 6,
|
13 |
+
"g": 2,
|
14 |
+
"h": 9,
|
15 |
+
"i": 10,
|
16 |
+
"j": 21,
|
17 |
+
"k": 14,
|
18 |
+
"l": 17,
|
19 |
+
"m": 1,
|
20 |
+
"n": 11,
|
21 |
+
"o": 25,
|
22 |
+
"p": 7,
|
23 |
+
"q": 15,
|
24 |
+
"r": 30,
|
25 |
+
"s": 12,
|
26 |
+
"t": 16,
|
27 |
+
"u": 27,
|
28 |
+
"v": 28,
|
29 |
+
"w": 33,
|
30 |
+
"x": 20,
|
31 |
+
"y": 31,
|
32 |
+
"z": 5,
|
33 |
+
"|": 34,
|
34 |
+
"Γ": 19,
|
35 |
+
"β": 26,
|
36 |
+
"β": 3,
|
37 |
+
"β": 29,
|
38 |
+
"β": 24
|
39 |
}
|