Upload tokenizer

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</s>": 40,
+  "<s>": 39,
+  "[PAD]": 38,
+  "[UNK]": 37
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "37": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 +1,41 @@
+{
+  "'": 20,
+  "[PAD]": 38,
+  "[UNK]": 37,
+  "`": 51,
+  "a": 12,
+  "b": 26,
+  "c": 7,
+  "d": 19,
+  "e": 1,
+  "f": 28,
+  "g": 6,
+  "h": 43,
+  "i": 0,
+  "j": 27,
+  "k": 31,
+  "l": 23,
+  "m": 37,
+  "n": 44,
+  "o": 48,
+  "p": 21,
+  "q": 35,
+  "r": 49,
+  "s": 46,
+  "t": 18,
+  "u": 25,
+  "v": 36,
+  "w": 4,
+  "x": 45,
+  "y": 42,
+  "z": 24,
+  "|": 52,
+  "`": 34,
+  "–": 39,
+  "—": 17,
+  "‘": 16,
+  "’": 47,
+  "“": 22,
+  "”": 15,
+  "‟": 38
+}