Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 66,
+  "<s>": 65
+}

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 +1,12 @@
+{
+  "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 +1,67 @@
+{
+  "[PAD]": 64,
+  "[UNK]": 63,
+  "|": 1,
+  "~": 0,
+  "ଁ": 2,
+  "ଂ": 3,
+  "ଃ": 4,
+  "ଅ": 5,
+  "ଆ": 6,
+  "ଇ": 7,
+  "ଈ": 8,
+  "ଉ": 9,
+  "ଊ": 10,
+  "ଏ": 11,
+  "ଓ": 12,
+  "କ": 13,
+  "ଖ": 14,
+  "ଗ": 15,
+  "ଘ": 16,
+  "ଙ": 17,
+  "ଚ": 18,
+  "ଛ": 19,
+  "ଜ": 20,
+  "ଝ": 21,
+  "ଞ": 22,
+  "ଟ": 23,
+  "ଠ": 24,
+  "ଡ": 25,
+  "ଢ": 26,
+  "ଣ": 27,
+  "ତ": 28,
+  "ଥ": 29,
+  "ଦ": 30,
+  "ଧ": 31,
+  "ନ": 32,
+  "ପ": 33,
+  "ଫ": 34,
+  "ବ": 35,
+  "ଭ": 36,
+  "ମ": 37,
+  "ଯ": 38,
+  "ର": 39,
+  "ଲ": 40,
+  "ଳ": 41,
+  "ଵ": 42,
+  "ଶ": 43,
+  "ଷ": 44,
+  "ସ": 45,
+  "ହ": 46,
+  "଼": 47,
+  "ା": 48,
+  "ି": 49,
+  "ୀ": 50,
+  "ୁ": 51,
+  "ୂ": 52,
+  "ୃ": 53,
+  "େ": 54,
+  "ୈ": 55,
+  "ୋ": 56,
+  "ୌ": 57,
+  "୍": 58,
+  "ୟ": 59,
+  "ୱ": 60,
+  "–": 61,
+  "’": 62
+}