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-53-Hindi-Version2
   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: hi_in
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.3987113150444206
+      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>": 113,
+  "<s>": 112
+}

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": {
+    "110": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "113": {
+      "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 +1,114 @@
+{
+  "$": 5,
+  "'": 29,
+  "+": 90,
+  "/": 45,
+  "0": 49,
+  "1": 24,
+  "2": 34,
+  "3": 44,
+  "4": 61,
+  "5": 53,
+  "6": 43,
+  "7": 96,
+  "8": 42,
+  "9": 21,
+  "[PAD]": 111,
+  "[UNK]": 110,
+  "a": 97,
+  "b": 71,
+  "c": 57,
+  "d": 76,
+  "e": 15,
+  "f": 89,
+  "g": 64,
+  "h": 9,
+  "i": 55,
+  "j": 20,
+  "k": 6,
+  "l": 41,
+  "m": 75,
+  "n": 72,
+  "o": 95,
+  "p": 83,
+  "q": 2,
+  "r": 65,
+  "s": 31,
+  "t": 78,
+  "u": 99,
+  "v": 88,
+  "w": 47,
+  "x": 80,
+  "y": 73,
+  "z": 81,
+  "|": 107,
+  "£": 19,
+  "¥": 98,
+  "°": 1,
+  "á": 85,
+  "õ": 37,
+  "ú": 12,
+  "ँ": 91,
+  "ं": 103,
+  "ः": 11,
+  "अ": 23,
+  "आ": 60,
+  "इ": 105,
+  "ई": 0,
+  "उ": 50,
+  "ऊ": 46,
+  "ए": 22,
+  "ऐ": 33,
+  "ऑ": 58,
+  "ओ": 30,
+  "औ": 104,
+  "क": 101,
+  "ख": 92,
+  "ग": 26,
+  "घ": 109,
+  "च": 62,
+  "छ": 32,
+  "ज": 18,
+  "झ": 69,
+  "ञ": 68,
+  "ट": 3,
+  "ठ": 39,
+  "ड": 87,
+  "ढ": 35,
+  "ण": 106,
+  "त": 79,
+  "थ": 48,
+  "द": 27,
+  "ध": 10,
+  "न": 25,
+  "प": 70,
+  "फ": 108,
+  "ब": 16,
+  "भ": 38,
+  "म": 84,
+  "य": 28,
+  "र": 36,
+  "ल": 52,
+  "व": 74,
+  "श": 77,
+  "ष": 54,
+  "स": 100,
+  "ह": 7,
+  "़": 8,
+  "ा": 51,
+  "ि": 67,
+  "ी": 4,
+  "ु": 13,
+  "ू": 94,
+  "ृ": 86,
+  "े": 14,
+  "ै": 56,
+  "ॉ": 17,
+  "ो": 93,
+  "ौ": 102,
+  "्": 40,
+  "।": 59,
+  "​": 63,
+  "‍": 82,
+  "—": 66
+}