Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "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": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,70 @@
+{
+  "!": 60,
+  "\"": 50,
+  "-": 16,
+  ".": 51,
+  ":": 35,
+  ";": 11,
+  "[PAD]": 67,
+  "[UNK]": 66,
+  "|": 21,
+  "،": 8,
+  "؟": 34,
+  "ا": 12,
+  "ل": 59,
+  "ه": 63,
+  "ّ": 6,
+  "ހ": 41,
+  "ށ": 46,
+  "ނ": 32,
+  "ރ": 39,
+  "ބ": 13,
+  "ޅ": 1,
+  "ކ": 18,
+  "އ": 62,
+  "ވ": 40,
+  "މ": 65,
+  "ފ": 43,
+  "ދ": 5,
+  "ތ": 45,
+  "ލ": 3,
+  "ގ": 29,
+  "ޏ": 0,
+  "ސ": 49,
+  "ޑ": 26,
+  "ޒ": 9,
+  "ޓ": 64,
+  "ޔ": 14,
+  "ޕ": 19,
+  "ޖ": 52,
+  "ޗ": 33,
+  "ޘ": 15,
+  "ޙ": 23,
+  "ޚ": 4,
+  "ޛ": 37,
+  "ޝ": 57,
+  "ޞ": 25,
+  "ޟ": 20,
+  "ޠ": 24,
+  "ޡ": 61,
+  "ޢ": 2,
+  "ޣ": 10,
+  "ޤ": 31,
+  "ޥ": 47,
+  "ަ": 54,
+  "ާ": 36,
+  "ި": 22,
+  "ީ": 17,
+  "ު": 53,
+  "ޫ": 38,
+  "ެ": 27,
+  "ޭ": 56,
+  "ޮ": 58,
+  "ޯ": 28,
+  "ް": 44,
+  "–": 42,
+  "‘": 30,
+  "’": 55,
+  "ﷲ": 48,
+  "ﷺ": 7
+}