Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 71,
+  "<s>": 70,
+  "[PAD]": 69,
+  "[UNK]": 68
+}

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 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "68": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "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": "tha",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,74 @@
+{
+  "tha": {
+    "[PAD]": 69,
+    "[UNK]": 68,
+    "|": 0,
+    "ก": 1,
+    "ข": 2,
+    "ค": 3,
+    "ฆ": 4,
+    "ง": 5,
+    "จ": 6,
+    "ฉ": 7,
+    "ช": 8,
+    "ซ": 9,
+    "ญ": 10,
+    "ฎ": 11,
+    "ฏ": 12,
+    "ฐ": 13,
+    "ฑ": 14,
+    "ฒ": 15,
+    "ณ": 16,
+    "ด": 17,
+    "ต": 18,
+    "ถ": 19,
+    "ท": 20,
+    "ธ": 21,
+    "น": 22,
+    "บ": 23,
+    "ป": 24,
+    "ผ": 25,
+    "ฝ": 26,
+    "พ": 27,
+    "ฟ": 28,
+    "ภ": 29,
+    "ม": 30,
+    "ย": 31,
+    "ร": 32,
+    "ฤ": 33,
+    "ล": 34,
+    "ว": 35,
+    "ศ": 36,
+    "ษ": 37,
+    "ส": 38,
+    "ห": 39,
+    "ฬ": 40,
+    "อ": 41,
+    "ฮ": 42,
+    "ะ": 43,
+    "ั": 44,
+    "า": 45,
+    "ำ": 46,
+    "ิ": 47,
+    "ี": 48,
+    "ึ": 49,
+    "ื": 50,
+    "ุ": 51,
+    "ู": 52,
+    "เ": 53,
+    "แ": 54,
+    "โ": 55,
+    "ใ": 56,
+    "ไ": 57,
+    "ๅ": 58,
+    "ๆ": 59,
+    "็": 60,
+    "่": 61,
+    "้": 62,
+    "๊": 63,
+    "๋": 64,
+    "์": 65,
+    "ํ": 66,
+    "’": 67
+  }
+}