Upload 5 files
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +49 -0
- vocab.json +39 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 38,
|
| 3 |
+
"[UNK]": 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 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"do_lower_case": false,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"extra_special_tokens": {},
|
| 41 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
+
"pad_token": "<pad>",
|
| 43 |
+
"processor_class": "Wav2Vec2Processor",
|
| 44 |
+
"replace_word_delimiter_char": " ",
|
| 45 |
+
"target_lang": null,
|
| 46 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 47 |
+
"unk_token": "<unk>",
|
| 48 |
+
"word_delimiter_token": "|"
|
| 49 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<pad>": 0,
|
| 4 |
+
"<s>": 1,
|
| 5 |
+
"<unk>": 3,
|
| 6 |
+
"|": 4,
|
| 7 |
+
"а": 5,
|
| 8 |
+
"б": 6,
|
| 9 |
+
"в": 7,
|
| 10 |
+
"г": 8,
|
| 11 |
+
"д": 9,
|
| 12 |
+
"е": 10,
|
| 13 |
+
"ж": 11,
|
| 14 |
+
"з": 12,
|
| 15 |
+
"и": 13,
|
| 16 |
+
"й": 14,
|
| 17 |
+
"к": 15,
|
| 18 |
+
"л": 16,
|
| 19 |
+
"м": 17,
|
| 20 |
+
"н": 18,
|
| 21 |
+
"о": 19,
|
| 22 |
+
"п": 20,
|
| 23 |
+
"р": 21,
|
| 24 |
+
"с": 22,
|
| 25 |
+
"т": 23,
|
| 26 |
+
"у": 24,
|
| 27 |
+
"ф": 25,
|
| 28 |
+
"х": 26,
|
| 29 |
+
"ц": 27,
|
| 30 |
+
"ч": 28,
|
| 31 |
+
"ш": 29,
|
| 32 |
+
"щ": 30,
|
| 33 |
+
"ъ": 31,
|
| 34 |
+
"ы": 32,
|
| 35 |
+
"ь": 33,
|
| 36 |
+
"э": 34,
|
| 37 |
+
"ю": 35,
|
| 38 |
+
"я": 36
|
| 39 |
+
}
|