Upload tokenizer

README.md

@@ -11,8 +11,8 @@ model-index:
 - name: wav2vec2-romanian-test
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_17_0
       type: common_voice_17_0
@@ -20,9 +20,9 @@ model-index:
       split: validation
       args: ro
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.9992270033496522
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

added_tokens.json

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

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "41": {
+    "42": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "42": {
+    "43": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "43": {
+    "44": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "44": {
+    "45": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -34,9 +34,10 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "do_lower_case": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",

vocab.json

@@ -1,45 +1,46 @@
 {
-  " ": 12,
-  "[PAD]": 42,
-  "[UNK]": 41,
-  "a": 3,
-  "b": 11,
-  "c": 2,
-  "d": 21,
-  "e": 26,
-  "f": 24,
-  "g": 28,
-  "h": 31,
-  "i": 9,
-  "j": 8,
-  "k": 20,
-  "l": 32,
-  "m": 16,
-  "n": 18,
-  "o": 30,
-  "p": 23,
-  "q": 27,
-  "r": 38,
-  "s": 33,
-  "t": 0,
-  "u": 36,
-  "v": 4,
-  "w": 13,
-  "x": 25,
-  "y": 39,
+  " ": 14,
+  "[PAD]": 43,
+  "[UNK]": 42,
+  "a": 7,
+  "b": 36,
+  "c": 27,
+  "d": 5,
+  "e": 2,
+  "f": 32,
+  "g": 17,
+  "h": 3,
+  "i": 12,
+  "j": 37,
+  "k": 28,
+  "l": 18,
+  "m": 0,
+  "n": 15,
+  "o": 41,
+  "p": 4,
+  "q": 39,
+  "r": 6,
+  "s": 1,
+  "t": 23,
+  "u": 16,
+  "v": 25,
+  "w": 31,
+  "x": 9,
+  "y": 11,
   "z": 29,
-  "á": 22,
-  "â": 10,
-  "é": 17,
-  "î": 14,
-  "ü": 37,
-  "ă": 35,
-  "ć": 6,
-  "đ": 19,
-  "ş": 7,
-  "š": 5,
-  "ţ": 1,
-  "ș": 34,
-  "ț": 15,
-  "”": 40
+  "á": 40,
+  "â": 33,
+  "é": 21,
+  "î": 19,
+  "ü": 22,
+  "ă": 30,
+  "ć": 24,
+  "č": 34,
+  "đ": 8,
+  "ş": 13,
+  "š": 38,
+  "ţ": 10,
+  "ș": 20,
+  "ț": 35,
+  "”": 26
 }