Upload tokenizer

README.md

@@ -1,19 +1,19 @@
 ---
-library_name: transformers
-license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
-tags:
-- generated_from_trainer
 datasets:
 - fleurs
+library_name: transformers
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-large-xlsr-oria-v0
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: fleurs
       type: fleurs
@@ -21,9 +21,9 @@ model-index:
       split: None
       args: or_in
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.4972150445018662
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 131,
+  "<s>": 130
+}

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": {
+    "128": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "131": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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 +1,132 @@
+{
+  "$": 121,
+  "'": 78,
+  "*": 66,
+  "+": 64,
+  "/": 75,
+  "0": 117,
+  "1": 16,
+  "2": 90,
+  "3": 73,
+  "4": 45,
+  "5": 86,
+  "6": 61,
+  "7": 31,
+  "8": 92,
+  "9": 77,
+  "[": 25,
+  "[PAD]": 129,
+  "[UNK]": 128,
+  "]": 79,
+  "a": 50,
+  "b": 116,
+  "c": 5,
+  "d": 113,
+  "e": 33,
+  "f": 69,
+  "g": 8,
+  "h": 15,
+  "i": 99,
+  "j": 37,
+  "k": 91,
+  "l": 94,
+  "m": 115,
+  "n": 82,
+  "o": 6,
+  "p": 59,
+  "q": 35,
+  "r": 60,
+  "s": 103,
+  "t": 55,
+  "u": 102,
+  "v": 57,
+  "w": 76,
+  "x": 67,
+  "y": 109,
+  "z": 24,
+  "|": 20,
+  "£": 1,
+  "¥": 0,
+  "°": 27,
+  "½": 84,
+  "¾": 87,
+  "õ": 2,
+  "।": 36,
+  "ଁ": 47,
+  "ଂ": 96,
+  "ଃ": 38,
+  "ଅ": 29,
+  "ଆ": 95,
+  "ଇ": 9,
+  "ଈ": 68,
+  "ଉ": 100,
+  "ଊ": 40,
+  "ଋ": 19,
+  "ଏ": 11,
+  "ଐ": 39,
+  "ଓ": 110,
+  "ଔ": 48,
+  "କ": 44,
+  "ଖ": 7,
+  "ଗ": 42,
+  "ଘ": 13,
+  "ଙ": 65,
+  "ଚ": 28,
+  "ଛ": 120,
+  "ଜ": 30,
+  "ଝ": 118,
+  "ଞ": 89,
+  "ଟ": 43,
+  "ଠ": 46,
+  "ଡ": 21,
+  "ଢ": 56,
+  "ଣ": 107,
+  "ତ": 51,
+  "ଥ": 97,
+  "ଦ": 105,
+  "ଧ": 123,
+  "ନ": 122,
+  "ପ": 93,
+  "ଫ": 12,
+  "ବ": 101,
+  "ଭ": 85,
+  "ମ": 81,
+  "ଯ": 32,
+  "ର": 34,
+  "ଲ": 49,
+  "ଳ": 114,
+  "ଵ": 58,
+  "ଶ": 14,
+  "ଷ": 23,
+  "ସ": 80,
+  "ହ": 41,
+  "଼": 10,
+  "ା": 71,
+  "ି": 52,
+  "ୀ": 125,
+  "ୁ": 119,
+  "ୂ": 74,
+  "ୃ": 104,
+  "ୄ": 124,
+  "େ": 88,
+  "ୈ": 3,
+  "ୋ": 72,
+  "ୌ": 4,
+  "୍": 112,
+  "ୗ": 54,
+  "ୟ": 63,
+  "୦": 17,
+  "୧": 83,
+  "୨": 111,
+  "୩": 70,
+  "୪": 53,
+  "୬": 106,
+  "୭": 26,
+  "ୱ": 18,
+  "​": 98,
+  "‌": 62,
+  "‍": 108,
+  "–": 22,
+  "—": 127,
+  "’": 126
+}