Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-large-xlsr-53
 metrics:
 - wer
 model-index:

tokenizer_config.json

@@ -19,7 +19,7 @@
     "40": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -27,7 +27,7 @@
     "41": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

vocab.json

@@ -1,42 +1,42 @@
 {
-  "'": 34,
+  "'": 17,
   "[PAD]": 39,
   "[UNK]": 38,
-  "a": 6,
-  "b": 26,
-  "c": 4,
-  "d": 1,
-  "e": 19,
-  "f": 18,
-  "g": 20,
-  "h": 37,
+  "a": 12,
+  "b": 14,
+  "c": 7,
+  "d": 15,
+  "e": 0,
+  "f": 21,
+  "g": 2,
+  "h": 9,
   "i": 29,
-  "j": 7,
-  "k": 30,
-  "l": 28,
-  "m": 25,
-  "n": 27,
-  "o": 2,
-  "p": 0,
-  "q": 35,
-  "r": 36,
-  "s": 31,
-  "t": 5,
-  "u": 12,
-  "v": 15,
-  "w": 22,
-  "x": 33,
+  "j": 37,
+  "k": 11,
+  "l": 30,
+  "m": 13,
+  "n": 32,
+  "o": 24,
+  "p": 25,
+  "q": 27,
+  "r": 1,
+  "s": 23,
+  "t": 22,
+  "u": 20,
+  "v": 28,
+  "w": 5,
+  "x": 4,
   "y": 3,
-  "z": 32,
-  "|": 24,
-  "à": 16,
-  "â": 14,
-  "è": 23,
-  "é": 21,
-  "ê": 11,
-  "ñ": 10,
-  "ô": 8,
-  "ù": 13,
-  "û": 17,
-  "ü": 9
+  "z": 31,
+  "|": 8,
+  "à": 34,
+  "â": 26,
+  "è": 33,
+  "é": 35,
+  "ê": 16,
+  "ñ": 6,
+  "ô": 10,
+  "ù": 36,
+  "û": 18,
+  "ü": 19
 }