Upload processor
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +40 -0
- vocab.json +39 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 38,
|
3 |
+
"[PAD]": 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,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"36": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"37": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"38": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"bos_token": "<s>",
|
29 |
+
"clean_up_tokenization_spaces": true,
|
30 |
+
"do_lower_case": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"model_max_length": 1000000000000000019884624838656,
|
33 |
+
"pad_token": "[PAD]",
|
34 |
+
"processor_class": "Wav2Vec2Processor",
|
35 |
+
"replace_word_delimiter_char": " ",
|
36 |
+
"target_lang": null,
|
37 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
38 |
+
"unk_token": "[UNK]",
|
39 |
+
"word_delimiter_token": "|"
|
40 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 28,
|
3 |
+
"[PAD]": 37,
|
4 |
+
"[UNK]": 36,
|
5 |
+
"|": 31,
|
6 |
+
"а": 22,
|
7 |
+
"б": 32,
|
8 |
+
"в": 5,
|
9 |
+
"г": 27,
|
10 |
+
"д": 8,
|
11 |
+
"е": 21,
|
12 |
+
"ж": 19,
|
13 |
+
"з": 33,
|
14 |
+
"и": 7,
|
15 |
+
"й": 0,
|
16 |
+
"к": 18,
|
17 |
+
"л": 1,
|
18 |
+
"м": 17,
|
19 |
+
"н": 3,
|
20 |
+
"о": 34,
|
21 |
+
"п": 29,
|
22 |
+
"р": 26,
|
23 |
+
"с": 25,
|
24 |
+
"т": 15,
|
25 |
+
"у": 13,
|
26 |
+
"ф": 6,
|
27 |
+
"х": 20,
|
28 |
+
"ц": 12,
|
29 |
+
"ч": 4,
|
30 |
+
"ш": 30,
|
31 |
+
"щ": 24,
|
32 |
+
"ъ": 2,
|
33 |
+
"ы": 10,
|
34 |
+
"ь": 9,
|
35 |
+
"э": 16,
|
36 |
+
"ю": 14,
|
37 |
+
"я": 11,
|
38 |
+
"ё": 23
|
39 |
+
}
|