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-Version3
   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: 0.282143903153373
+      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 @@
+{
+  "$": 86,
+  "'": 107,
+  "+": 4,
+  "/": 73,
+  "0": 41,
+  "1": 13,
+  "2": 22,
+  "3": 16,
+  "4": 100,
+  "5": 30,
+  "6": 18,
+  "7": 24,
+  "8": 54,
+  "9": 96,
+  "[PAD]": 111,
+  "[UNK]": 110,
+  "a": 90,
+  "b": 11,
+  "c": 28,
+  "d": 62,
+  "e": 26,
+  "f": 44,
+  "g": 52,
+  "h": 109,
+  "i": 99,
+  "j": 103,
+  "k": 40,
+  "l": 19,
+  "m": 47,
+  "n": 66,
+  "o": 46,
+  "p": 108,
+  "q": 78,
+  "r": 51,
+  "s": 75,
+  "t": 57,
+  "u": 34,
+  "v": 21,
+  "w": 97,
+  "x": 15,
+  "y": 77,
+  "z": 85,
+  "|": 10,
+  "£": 76,
+  "¥": 25,
+  "°": 87,
+  "á": 39,
+  "õ": 27,
+  "ú": 72,
+  "ँ": 104,
+  "ं": 58,
+  "ः": 56,
+  "अ": 38,
+  "आ": 29,
+  "इ": 49,
+  "ई": 42,
+  "उ": 80,
+  "ऊ": 35,
+  "ए": 12,
+  "ऐ": 82,
+  "ऑ": 79,
+  "ओ": 69,
+  "औ": 6,
+  "क": 102,
+  "ख": 94,
+  "ग": 33,
+  "घ": 23,
+  "च": 64,
+  "छ": 98,
+  "ज": 55,
+  "झ": 2,
+  "ञ": 48,
+  "ट": 65,
+  "ठ": 20,
+  "ड": 91,
+  "ढ": 70,
+  "ण": 3,
+  "त": 63,
+  "थ": 95,
+  "द": 71,
+  "ध": 93,
+  "न": 60,
+  "प": 88,
+  "फ": 67,
+  "ब": 59,
+  "भ": 8,
+  "म": 92,
+  "य": 9,
+  "र": 61,
+  "ल": 14,
+  "व": 68,
+  "श": 53,
+  "ष": 74,
+  "स": 5,
+  "ह": 105,
+  "़": 31,
+  "ा": 81,
+  "ि": 7,
+  "ी": 36,
+  "ु": 83,
+  "ू": 0,
+  "ृ": 101,
+  "े": 32,
+  "ै": 106,
+  "ॉ": 37,
+  "ो": 84,
+  "ौ": 50,
+  "्": 43,
+  "।": 17,
+  "​": 89,
+  "‍": 45,
+  "—": 1
+}