VSydorskyi
commited on
Commit
•
3e5b968
1
Parent(s):
f06efa2
add model
Browse files- added_tokens.json +1 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 54, "</s>": 55}
|
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": false,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "processor_class": "Wav2Vec2Processor", "special_tokens_map_file": "../logdirs/torch_asr_on_ukrainian_data2vec_cosinev3/special_tokens_map.json", "name_or_path": "../logdirs/torch_asr_on_ukrainian_data2vec_cosinev3/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"e": 0, "г": 1, "i": 2, "б": 3, "y": 4, "д": 5, "՚": 6, "m": 7, "й": 8, "ґ": 9, "k": 10, "к": 11, "a": 12, "л": 13, "р": 14, "’": 15, "ю": 16, "ш": 17, "н": 18, "ь": 19, "щ": 20, "і": 21, "ц": 22, "и": 23, "т": 25, "ж": 26, "x": 27, "́": 28, "є": 29, "в": 30, "j": 31, "о": 32, "з": 33, "м": 34, "ы": 35, "а": 36, "я": 37, "п": 38, "o": 39, "u": 40, "ї": 41, "n": 42, "ф": 43, "p": 44, "х": 45, "ч": 46, "с": 47, "c": 48, "е": 49, "у": 50, "l": 51, "|": 24, "[UNK]": 52, "[PAD]": 53}
|