Upload processor
Browse files- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +15 -0
- vocab.json +42 -0
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 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "Ar4ikov/wavlm-standart-russian-resd",
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"processor_class": "Wav2Vec2Processor",
|
9 |
+
"replace_word_delimiter_char": " ",
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
12 |
+
"tokenizer_file": null,
|
13 |
+
"unk_token": "<unk>",
|
14 |
+
"word_delimiter_token": "|"
|
15 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 5,
|
3 |
+
"-": 6,
|
4 |
+
"</s>": 2,
|
5 |
+
"<pad>": 0,
|
6 |
+
"<s>": 1,
|
7 |
+
"<unk>": 3,
|
8 |
+
"|": 4,
|
9 |
+
"а": 7,
|
10 |
+
"б": 8,
|
11 |
+
"в": 9,
|
12 |
+
"г": 10,
|
13 |
+
"д": 11,
|
14 |
+
"е": 12,
|
15 |
+
"ж": 13,
|
16 |
+
"з": 14,
|
17 |
+
"и": 15,
|
18 |
+
"й": 16,
|
19 |
+
"к": 17,
|
20 |
+
"л": 18,
|
21 |
+
"м": 19,
|
22 |
+
"н": 20,
|
23 |
+
"о": 21,
|
24 |
+
"п": 22,
|
25 |
+
"р": 23,
|
26 |
+
"с": 24,
|
27 |
+
"т": 25,
|
28 |
+
"у": 26,
|
29 |
+
"ф": 27,
|
30 |
+
"х": 28,
|
31 |
+
"ц": 29,
|
32 |
+
"ч": 30,
|
33 |
+
"ш": 31,
|
34 |
+
"щ": 32,
|
35 |
+
"ъ": 33,
|
36 |
+
"ы": 34,
|
37 |
+
"ь": 35,
|
38 |
+
"э": 36,
|
39 |
+
"ю": 37,
|
40 |
+
"я": 38,
|
41 |
+
"ё": 39
|
42 |
+
}
|