Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 55,
+  "<s>": 54
+}

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 +1,13 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,56 @@
+{
+  "[PAD]": 53,
+  "[UNK]": 52,
+  "|": 0,
+  "ّ": 1,
+  "ހ": 2,
+  "ށ": 3,
+  "ނ": 4,
+  "ރ": 5,
+  "ބ": 6,
+  "ޅ": 7,
+  "ކ": 8,
+  "އ": 9,
+  "ވ": 10,
+  "މ": 11,
+  "ފ": 12,
+  "ދ": 13,
+  "ތ": 14,
+  "ލ": 15,
+  "ގ": 16,
+  "ޏ": 17,
+  "ސ": 18,
+  "ޑ": 19,
+  "ޒ": 20,
+  "ޓ": 21,
+  "ޔ": 22,
+  "ޕ": 23,
+  "ޖ": 24,
+  "ޗ": 25,
+  "ޘ": 26,
+  "ޙ": 27,
+  "ޚ": 28,
+  "ޛ": 29,
+  "ޝ": 30,
+  "ޞ": 31,
+  "ޟ": 32,
+  "ޠ": 33,
+  "ޡ": 34,
+  "ޢ": 35,
+  "ޣ": 36,
+  "ޤ": 37,
+  "ޥ": 38,
+  "ަ": 39,
+  "ާ": 40,
+  "ި": 41,
+  "ީ": 42,
+  "ު": 43,
+  "ޫ": 44,
+  "ެ": 45,
+  "ޭ": 46,
+  "ޮ": 47,
+  "ޯ": 48,
+  "ް": 49,
+  "ﷲ": 50,
+  "ﷺ": 51
+}