Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 60,
+  "<s>": 59
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "57": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "dz",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,63 @@
+{
+  "dz": {
+    "*": 1,
+    "[PAD]": 58,
+    "[UNK]": 57,
+    "|": 0,
+    "་": 2,
+    "།": 3,
+    "ཀ": 4,
+    "ཁ": 5,
+    "ག": 6,
+    "ང": 7,
+    "ཅ": 8,
+    "ཆ": 9,
+    "ཇ": 10,
+    "ཉ": 11,
+    "ཊ": 12,
+    "ཏ": 13,
+    "ཐ": 14,
+    "ད": 15,
+    "ན": 16,
+    "པ": 17,
+    "ཕ": 18,
+    "བ": 19,
+    "མ": 20,
+    "ཙ": 21,
+    "ཚ": 22,
+    "ཛ": 23,
+    "ཝ": 24,
+    "ཞ": 25,
+    "ཟ": 26,
+    "འ": 27,
+    "ཡ": 28,
+    "ར": 29,
+    "ལ": 30,
+    "ཤ": 31,
+    "ས": 32,
+    "ཧ": 33,
+    "ཨ": 34,
+    "ཱ": 35,
+    "ི": 36,
+    "ུ": 37,
+    "ེ": 38,
+    "ོ": 39,
+    "ྐ": 40,
+    "ྒ": 41,
+    "ྔ": 42,
+    "ྗ": 43,
+    "ྟ": 44,
+    "ྡ": 45,
+    "ྣ": 46,
+    "ྤ": 47,
+    "ྦ": 48,
+    "ྨ": 49,
+    "ྩ": 50,
+    "ྫ": 51,
+    "ྭ": 52,
+    "ྱ": 53,
+    "ྲ": 54,
+    "ླ": 55,
+    "ྷ": 56
+  }
+}