Commit
•
edd1498
1
Parent(s):
de4dcee
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 +83 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 82,
|
| 3 |
+
"<s>": 81
|
| 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": false,
|
| 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": null,
|
| 11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 12 |
+
"unk_token": "[UNK]",
|
| 13 |
+
"word_delimiter_token": "|"
|
| 14 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"'": 53,
|
| 3 |
+
"/": 1,
|
| 4 |
+
"[PAD]": 80,
|
| 5 |
+
"[UNK]": 79,
|
| 6 |
+
"|": 43,
|
| 7 |
+
"।": 36,
|
| 8 |
+
"॥": 17,
|
| 9 |
+
"ঁ": 56,
|
| 10 |
+
"ং": 15,
|
| 11 |
+
"ঃ": 66,
|
| 12 |
+
"অ": 11,
|
| 13 |
+
"আ": 61,
|
| 14 |
+
"ই": 55,
|
| 15 |
+
"ঈ": 20,
|
| 16 |
+
"উ": 23,
|
| 17 |
+
"ঊ": 10,
|
| 18 |
+
"ঋ": 54,
|
| 19 |
+
"এ": 65,
|
| 20 |
+
"ঐ": 71,
|
| 21 |
+
"ও": 12,
|
| 22 |
+
"ঔ": 46,
|
| 23 |
+
"ক": 30,
|
| 24 |
+
"খ": 40,
|
| 25 |
+
"গ": 75,
|
| 26 |
+
"ঘ": 28,
|
| 27 |
+
"ঙ": 26,
|
| 28 |
+
"চ": 58,
|
| 29 |
+
"ছ": 68,
|
| 30 |
+
"জ": 62,
|
| 31 |
+
"ঝ": 34,
|
| 32 |
+
"ঞ": 76,
|
| 33 |
+
"ট": 7,
|
| 34 |
+
"ঠ": 16,
|
| 35 |
+
"ড": 13,
|
| 36 |
+
"ঢ": 25,
|
| 37 |
+
"ণ": 2,
|
| 38 |
+
"ত": 22,
|
| 39 |
+
"থ": 63,
|
| 40 |
+
"দ": 51,
|
| 41 |
+
"ধ": 3,
|
| 42 |
+
"ন": 45,
|
| 43 |
+
"প": 32,
|
| 44 |
+
"ফ": 18,
|
| 45 |
+
"ব": 48,
|
| 46 |
+
"ভ": 8,
|
| 47 |
+
"ম": 21,
|
| 48 |
+
"য": 50,
|
| 49 |
+
"র": 64,
|
| 50 |
+
"ল": 70,
|
| 51 |
+
"শ": 47,
|
| 52 |
+
"ষ": 39,
|
| 53 |
+
"স": 59,
|
| 54 |
+
"হ": 5,
|
| 55 |
+
"়": 31,
|
| 56 |
+
"া": 72,
|
| 57 |
+
"ি": 35,
|
| 58 |
+
"ী": 6,
|
| 59 |
+
"ু": 24,
|
| 60 |
+
"ূ": 4,
|
| 61 |
+
"ৃ": 41,
|
| 62 |
+
"ে": 38,
|
| 63 |
+
"ৈ": 77,
|
| 64 |
+
"ো": 74,
|
| 65 |
+
"ৌ": 49,
|
| 66 |
+
"্": 60,
|
| 67 |
+
"ৎ": 33,
|
| 68 |
+
"ৗ": 57,
|
| 69 |
+
"ড়": 78,
|
| 70 |
+
"ঢ়": 27,
|
| 71 |
+
"য়": 14,
|
| 72 |
+
"ৰ": 19,
|
| 73 |
+
"৵": 44,
|
| 74 |
+
"৷": 69,
|
| 75 |
+
"–": 42,
|
| 76 |
+
"—": 73,
|
| 77 |
+
"‘": 0,
|
| 78 |
+
"’": 37,
|
| 79 |
+
"‚": 52,
|
| 80 |
+
"“": 67,
|
| 81 |
+
"”": 29,
|
| 82 |
+
"…": 9
|
| 83 |
+
}
|