Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
-tags:
-- generated_from_trainer
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: xlsr-big-knnn
   results: []

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 28,
+  "<s>": 27
+}

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": {
+    "25": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "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 +1,29 @@
+{
+  "D": 8,
+  "O": 11,
+  "T": 15,
+  "[PAD]": 26,
+  "[UNK]": 25,
+  "a": 1,
+  "b": 12,
+  "c": 24,
+  "d": 22,
+  "e": 5,
+  "g": 7,
+  "h": 3,
+  "i": 4,
+  "j": 18,
+  "k": 21,
+  "l": 6,
+  "m": 19,
+  "n": 2,
+  "o": 23,
+  "p": 17,
+  "r": 20,
+  "s": 16,
+  "t": 14,
+  "u": 0,
+  "v": 10,
+  "y": 13,
+  "|": 9
+}