Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 57,
-  "<s>": 56
+  "</s>": 44,
+  "<s>": 43
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "54": {
+    "41": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "55": {
+    "42": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "56": {
+    "43": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "57": {
+    "44": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -41,7 +41,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
-  "target_lang": "ar",
+  "target_lang": "fr",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json

@@ -57,6 +57,51 @@
     "ّ": 52,
     "ْ": 53
   },
+  "fr": {
+    "3": 1,
+    "6": 2,
+    "[PAD]": 42,
+    "[UNK]": 41,
+    "a": 3,
+    "b": 4,
+    "c": 5,
+    "d": 6,
+    "e": 7,
+    "f": 8,
+    "g": 9,
+    "h": 10,
+    "i": 11,
+    "j": 12,
+    "k": 13,
+    "l": 14,
+    "m": 15,
+    "n": 16,
+    "o": 17,
+    "p": 18,
+    "q": 19,
+    "r": 20,
+    "s": 21,
+    "t": 22,
+    "u": 23,
+    "v": 24,
+    "w": 25,
+    "x": 26,
+    "y": 27,
+    "z": 28,
+    "|": 0,
+    "à": 29,
+    "â": 30,
+    "ç": 31,
+    "è": 32,
+    "é": 33,
+    "ê": 34,
+    "î": 35,
+    "ï": 36,
+    "ô": 37,
+    "ù": 38,
+    "û": 39,
+    "œ": 40
+  },
   "kab": {
     "$": 1,
     "0": 2,