add tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 73,
+  "<s>": 72
+}

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 +1,74 @@
+{
+  "/": 1,
+  "[PAD]": 71,
+  "[UNK]": 70,
+  "|": 0,
+  "।": 2,
+  "॥": 3,
+  "ঁ": 4,
+  "ং": 5,
+  "ঃ": 6,
+  "অ": 7,
+  "আ": 8,
+  "ই": 9,
+  "ঈ": 10,
+  "উ": 11,
+  "ঊ": 12,
+  "ঋ": 13,
+  "এ": 14,
+  "ঐ": 15,
+  "ও": 16,
+  "ঔ": 17,
+  "ক": 18,
+  "খ": 19,
+  "গ": 20,
+  "ঘ": 21,
+  "ঙ": 22,
+  "চ": 23,
+  "ছ": 24,
+  "জ": 25,
+  "ঝ": 26,
+  "ঞ": 27,
+  "ট": 28,
+  "ঠ": 29,
+  "ড": 30,
+  "ঢ": 31,
+  "ণ": 32,
+  "ত": 33,
+  "থ": 34,
+  "দ": 35,
+  "ধ": 36,
+  "ন": 37,
+  "প": 38,
+  "ফ": 39,
+  "ব": 40,
+  "ভ": 41,
+  "ম": 42,
+  "য": 43,
+  "র": 44,
+  "ল": 45,
+  "শ": 46,
+  "ষ": 47,
+  "স": 48,
+  "হ": 49,
+  "়": 50,
+  "া": 51,
+  "ি": 52,
+  "ী": 53,
+  "ু": 54,
+  "ূ": 55,
+  "ৃ": 56,
+  "ে": 57,
+  "ৈ": 58,
+  "ো": 59,
+  "ৌ": 60,
+  "্": 61,
+  "ৎ": 62,
+  "ড়": 63,
+  "য়": 64,
+  "ৰ": 65,
+  "—": 66,
+  "’": 67,
+  "‚": 68,
+  "…": 69
+}