add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 86,
+  "<s>": 85
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,87 @@
+{
+  "!": 1,
+  "'": 2,
+  ",": 3,
+  "-": 4,
+  ".": 5,
+  ":": 6,
+  ";": 7,
+  "=": 8,
+  "?": 9,
+  "[PAD]": 84,
+  "[UNK]": 83,
+  "|": 0,
+  "।": 10,
+  "ঁ": 11,
+  "ং": 12,
+  "ঃ": 13,
+  "অ": 14,
+  "আ": 15,
+  "ই": 16,
+  "ঈ": 17,
+  "উ": 18,
+  "ঊ": 19,
+  "ঋ": 20,
+  "এ": 21,
+  "ঐ": 22,
+  "ও": 23,
+  "ঔ": 24,
+  "ক": 25,
+  "খ": 26,
+  "গ": 27,
+  "ঘ": 28,
+  "ঙ": 29,
+  "চ": 30,
+  "ছ": 31,
+  "জ": 32,
+  "ঝ": 33,
+  "ঞ": 34,
+  "ট": 35,
+  "ঠ": 36,
+  "ড": 37,
+  "ঢ": 38,
+  "ণ": 39,
+  "ত": 40,
+  "থ": 41,
+  "দ": 42,
+  "ধ": 43,
+  "ন": 44,
+  "প": 45,
+  "ফ": 46,
+  "ব": 47,
+  "ভ": 48,
+  "ম": 49,
+  "য": 50,
+  "র": 51,
+  "ল": 52,
+  "শ": 53,
+  "ষ": 54,
+  "স": 55,
+  "হ": 56,
+  "া": 57,
+  "ি": 58,
+  "ী": 59,
+  "ু": 60,
+  "ূ": 61,
+  "ৃ": 62,
+  "ে": 63,
+  "ৈ": 64,
+  "ো": 65,
+  "ৌ": 66,
+  "্": 67,
+  "ৎ": 68,
+  "ড়": 69,
+  "ঢ়": 70,
+  "য়": 71,
+  "০": 72,
+  "১": 73,
+  "২": 74,
+  "৩": 75,
+  "৪": 76,
+  "৫": 77,
+  "৬": 78,
+  "৭": 79,
+  "৮": 80,
+  "৯": 81,
+  "‍": 82
+}