Upload processor
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +22 -0
- tokenizer_config.json +14 -0
- vocab.json +41 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 38,
|
3 |
+
"<s>": 37
|
4 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<s>",
|
19 |
+
"eos_token": "</s>",
|
20 |
+
"pad_token": "[PAD]",
|
21 |
+
"unk_token": "[UNK]"
|
22 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"processor_class": "Wav2Vec2Processor",
|
9 |
+
"replace_word_delimiter_char": " ",
|
10 |
+
"target_lang": "fas",
|
11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
12 |
+
"unk_token": "[UNK]",
|
13 |
+
"word_delimiter_token": "|"
|
14 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"fas": {
|
3 |
+
"[PAD]": 36,
|
4 |
+
"[UNK]": 35,
|
5 |
+
"|": 0,
|
6 |
+
"آ": 1,
|
7 |
+
"ئ": 2,
|
8 |
+
"ا": 3,
|
9 |
+
"ب": 4,
|
10 |
+
"ت": 5,
|
11 |
+
"ث": 6,
|
12 |
+
"ج": 7,
|
13 |
+
"ح": 8,
|
14 |
+
"خ": 9,
|
15 |
+
"د": 10,
|
16 |
+
"ذ": 11,
|
17 |
+
"ر": 12,
|
18 |
+
"ز": 13,
|
19 |
+
"س": 14,
|
20 |
+
"ش": 15,
|
21 |
+
"ص": 16,
|
22 |
+
"ض": 17,
|
23 |
+
"ط": 18,
|
24 |
+
"ظ": 19,
|
25 |
+
"ع": 20,
|
26 |
+
"غ": 21,
|
27 |
+
"ف": 22,
|
28 |
+
"ق": 23,
|
29 |
+
"ل": 24,
|
30 |
+
"م": 25,
|
31 |
+
"ن": 26,
|
32 |
+
"ه": 27,
|
33 |
+
"و": 28,
|
34 |
+
"پ": 29,
|
35 |
+
"چ": 30,
|
36 |
+
"ژ": 31,
|
37 |
+
"ک": 32,
|
38 |
+
"گ": 33,
|
39 |
+
"ی": 34
|
40 |
+
}
|
41 |
+
}
|