Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 30,
+  "<s>": 29
+}

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 +1,13 @@
+{
+  "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 +1,31 @@
+{
+  "A": 1,
+  "B": 2,
+  "C": 3,
+  "D": 4,
+  "E": 5,
+  "F": 6,
+  "G": 7,
+  "H": 8,
+  "I": 9,
+  "J": 10,
+  "K": 11,
+  "L": 12,
+  "M": 13,
+  "N": 14,
+  "O": 15,
+  "P": 16,
+  "Q": 17,
+  "R": 18,
+  "S": 19,
+  "T": 20,
+  "U": 21,
+  "V": 22,
+  "W": 23,
+  "X": 24,
+  "Y": 25,
+  "Z": 26,
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "|": 0
+}