Upload tokenizer

added_tokens.json

@@ -1 +1,4 @@
-{"<s>": 40, "</s>": 41}
+{
+  "</s>": 42,
+  "<s>": 41
+}

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 +1,13 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "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 +1,43 @@
-{"a": 0, "aː": 1, "b": 2, "d": 3, "e": 4, "eː": 5, "f": 6, "h": 7, "i": 8, "iː": 9, "j": 10, "k": 11, "kʰ": 12, "l": 13, "m": 14, "n": 15, "o": 16, "oː": 17, "p": 18, "pʰ": 19, "r": 20, "s": 21, "t": 22, "t͡ɕ": 23, "t͡ɕʰ": 24, "u": 25, "uː": 26, "w": 27, "ŋ": 28, "ɔ": 29, "ɔː": 30, "ɛ": 31, "ɛː": 32, "ɤ": 33, "ɤː": 34, "ɯ": 35, "ɯː": 36, "ʔ": 37, "[UNK]": 38, "[PAD]": 39}
+{
+  "[PAD]": 40,
+  "[UNK]": 39,
+  "a": 0,
+  "aː": 1,
+  "b": 2,
+  "d": 3,
+  "e": 4,
+  "eː": 5,
+  "f": 6,
+  "h": 7,
+  "i": 8,
+  "iː": 9,
+  "j": 10,
+  "k": 11,
+  "kʰ": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "oː": 17,
+  "p": 18,
+  "pʰ": 19,
+  "r": 20,
+  "s": 21,
+  "t": 22,
+  "tʰ": 23,
+  "t͡ɕ": 24,
+  "t͡ɕʰ": 25,
+  "u": 26,
+  "uː": 27,
+  "w": 28,
+  "ŋ": 29,
+  "ɔ": 30,
+  "ɔː": 31,
+  "ɛ": 32,
+  "ɛː": 33,
+  "ɤ": 34,
+  "ɤː": 35,
+  "ɯ": 36,
+  "ɯː": 37,
+  "ʔ": 38
+}