Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 44,
-  "<s>": 43
+  "</s>": 46,
+  "<s>": 45
 }

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
-    "41": {
+    "43": {
       "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "42": {
+    "44": {
       "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "43": {
+    "45": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "44": {
+    "46": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,
@@ -35,14 +35,15 @@
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
+  "do_phonemize": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "phone_delimiter_token": " ",
+  "phonemizer_backend": "espeak",
+  "phonemizer_lang": "en-us",
   "processor_class": "Wav2Vec2Processor",
-  "replace_word_delimiter_char": " ",
-  "target_lang": null,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
   "unk_token": "[UNK]",
-  "word_delimiter_token": "|"
+  "word_delimiter_token": null
 }

vocab.json

@@ -1,7 +1,7 @@
 {
-  "[PAD]": 42,
-  "[UNK]": 41,
-  "|": 0,
+  " ": 0,
+  "[PAD]": 44,
+  "[UNK]": 43,
   "ء": 1,
   "آ": 2,
   "أ": 3,
@@ -9,37 +9,39 @@
   "إ": 5,
   "ئ": 6,
   "ا": 7,
-  "ب": 8,
-  "ة": 9,
-  "ت": 10,
-  "ث": 11,
-  "ج": 12,
-  "ح": 13,
-  "خ": 14,
-  "د": 15,
-  "ذ": 16,
-  "ر": 17,
-  "ز": 18,
-  "س": 19,
-  "ش": 20,
-  "ص": 21,
-  "ض": 22,
-  "ط": 23,
-  "ظ": 24,
-  "ع": 25,
-  "غ": 26,
-  "ف": 27,
-  "ق": 28,
-  "ك": 29,
-  "ل": 30,
-  "م": 31,
-  "ن": 32,
-  "ه": 33,
-  "و": 34,
-  "ى": 35,
-  "ي": 36,
-  "ً": 37,
-  "چ": 38,
-  "ک": 39,
-  "ی": 40
+  "اً": 8,
+  "ب": 9,
+  "ة": 10,
+  "ت": 11,
+  "ث": 12,
+  "ج": 13,
+  "ح": 14,
+  "خ": 15,
+  "د": 16,
+  "ذ": 17,
+  "ر": 18,
+  "ز": 19,
+  "س": 20,
+  "ش": 21,
+  "ص": 22,
+  "ض": 23,
+  "ط": 24,
+  "ظ": 25,
+  "ع": 26,
+  "غ": 27,
+  "ف": 28,
+  "ق": 29,
+  "ك": 30,
+  "ل": 31,
+  "لا": 32,
+  "م": 33,
+  "ن": 34,
+  "ه": 35,
+  "و": 36,
+  "ى": 37,
+  "ي": 38,
+  "چ": 39,
+  "ڨ": 40,
+  "ک": 41,
+  "ی": 42
 }