Upload tokenizer

README.md

@@ -1,18 +1,18 @@
 ---
-license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
-tags:
-- generated_from_trainer
 datasets:
 - common_voice_17_0
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: wav2vec2-large-xlsr-Mongolian-cv17-base
   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: mn
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 0.7902951968892054
+      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>": 42,
-  "<s>": 41
+  "</s>": 39,
+  "<s>": 38
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "39": {
+    "36": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "40": {
+    "37": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "41": {
+    "38": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "42": {
+    "39": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,43 +1,40 @@
 {
-  "'": 28,
-  "[PAD]": 40,
-  "[UNK]": 39,
-  "h": 18,
-  "|": 9,
-  "«": 4,
-  "»": 6,
-  "а": 34,
+  "[PAD]": 37,
+  "[UNK]": 36,
+  "h": 1,
+  "|": 5,
+  "а": 20,
   "б": 35,
-  "в": 12,
-  "г": 30,
-  "д": 27,
-  "е": 36,
-  "ж": 24,
-  "з": 15,
-  "и": 1,
-  "й": 20,
+  "в": 4,
+  "г": 25,
+  "д": 33,
+  "е": 18,
+  "ж": 34,
+  "з": 12,
+  "и": 22,
+  "й": 24,
   "к": 17,
-  "л": 3,
-  "м": 11,
-  "н": 2,
-  "о": 13,
-  "п": 14,
-  "р": 21,
-  "с": 22,
-  "т": 29,
-  "у": 0,
-  "ф": 38,
-  "х": 16,
-  "ц": 19,
-  "ч": 8,
-  "ш": 37,
-  "ъ": 5,
-  "ы": 33,
-  "ь": 25,
-  "э": 7,
-  "ю": 31,
-  "я": 26,
-  "ё": 10,
-  "ү": 32,
-  "ө": 23
+  "л": 28,
+  "м": 14,
+  "н": 15,
+  "о": 10,
+  "п": 6,
+  "р": 19,
+  "с": 9,
+  "т": 2,
+  "у": 7,
+  "ф": 23,
+  "х": 27,
+  "ц": 8,
+  "ч": 16,
+  "ш": 30,
+  "ъ": 29,
+  "ы": 13,
+  "ь": 31,
+  "э": 21,
+  "ю": 26,
+  "я": 11,
+  "ё": 32,
+  "ү": 3,
+  "ө": 0
 }