Upload tokenizer

README.md

@@ -12,8 +12,8 @@ model-index:
 - name: w2v2-lmk_original
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: audiofolder
       type: audiofolder
@@ -21,9 +21,9 @@ model-index:
       split: test
       args: default
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.5435540069686411
+      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>": 40,
-  "<s>": 39
+  "</s>": 39,
+  "<s>": 38
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "37": {
+    "36": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "38": {
+    "37": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "39": {
+    "38": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "40": {
+    "39": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,6 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json

@@ -8,8 +8,8 @@
   "7": 7,
   "8": 8,
   "9": 9,
-  "[PAD]": 38,
-  "[UNK]": 37,
+  "[PAD]": 37,
+  "[UNK]": 36,
   "a": 10,
   "b": 11,
   "c": 12,
@@ -36,6 +36,5 @@
   "x": 33,
   "y": 34,
   "z": 35,
-  "|": 0,
-  "…": 36
+  "|": 0
 }