Upload tokenizer

added_tokens.json

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

special_tokens_map.json

@@ -1 +1,22 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{
+  "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

@@ -1 +1,12 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "/kaggle/working/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": ".",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,44 @@
-{"aa": 1, "ae": 2, "ah": 3, "aw": 4, "ay": 5, "b": 6, "ch": 7, "d": 8, "dh": 9, "dx": 10, "eh": 11, "er": 12, "ey": 13, "f": 14, "g": 15, "h#": 16, "hh": 17, "ih": 18, "iy": 19, "jh": 20, "k": 21, "l": 22, "m": 23, "n": 24, "ng": 25, "ow": 26, "oy": 27, "p": 28, "r": 29, "s": 30, "sh": 31, "t": 32, "th": 33, "uh": 34, "uw": 35, "v": 36, "w": 37, "y": 38, "z": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}
+{
+  "[PAD]": 41,
+  "[UNK]": 40,
+  "aa": 1,
+  "ae": 2,
+  "ah": 3,
+  "aw": 4,
+  "ay": 5,
+  "b": 6,
+  "ch": 7,
+  "d": 8,
+  "dh": 9,
+  "dx": 10,
+  "eh": 11,
+  "er": 12,
+  "ey": 13,
+  "f": 14,
+  "g": 15,
+  "h#": 16,
+  "hh": 17,
+  "ih": 18,
+  "iy": 19,
+  "jh": 20,
+  "k": 21,
+  "l": 22,
+  "m": 23,
+  "n": 24,
+  "ng": 25,
+  "ow": 26,
+  "oy": 27,
+  "p": 28,
+  "r": 29,
+  "s": 30,
+  "sh": 31,
+  "t": 32,
+  "th": 33,
+  "uh": 34,
+  "uw": 35,
+  "v": 36,
+  "w": 37,
+  "y": 38,
+  "z": 39,
+  "|": 0
+}