Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 43,
+  "<s>": 42
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "40": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 +1,44 @@
+{
+  "[PAD]": 41,
+  "[UNK]": 40,
+  "|": 0,
+  " ": 1,
+  "င": 2,
+  "တ": 3,
+  "ထ": 4,
+  "ပ": 5,
+  "မ": 6,
+  "ယ": 7,
+  "လ": 8,
+  "ဝ": 9,
+  "သ": 10,
+  "ဢ": 11,
+  "ိ": 12,
+  "ီ": 13,
+  "ု": 14,
+  "ူ": 15,
+  "ေ": 16,
+  "ဵ": 17,
+  "း": 18,
+  "်": 19,
+  "ျ": 20,
+  "ြ": 21,
+  "ွ": 22,
+  "ၢ": 23,
+  "ၵ": 24,
+  "ၶ": 25,
+  "ၸ": 26,
+  "ၺ": 27,
+  "ၼ": 28,
+  "ၽ": 29,
+  "ၾ": 30,
+  "ႁ": 31,
+  "ႂ": 32,
+  "ႃ": 33,
+  "ႄ": 34,
+  "ႅ": 35,
+  "ႆ": 36,
+  "ႇ": 37,
+  "ႈ": 38,
+  "ႉ": 39
+}