Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: cc-by-nc-4.0
-base_model: utter-project/mHuBERT-147
 tags:
 - generated_from_trainer
+base_model: utter-project/mHuBERT-147
 datasets:
 - common_voice_15_0
 metrics:
@@ -11,8 +11,8 @@ model-index:
 - name: mHuBERT-147-br
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: common_voice_15_0
       type: common_voice_15_0
@@ -20,9 +20,9 @@ model-index:
       split: None
       args: br
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 53.76572908956329
+      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>": 49,
-  "<s>": 48
+  "</s>": 50,
+  "<s>": 49
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "46": {
+    "47": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "47": {
+    "48": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "48": {
+    "49": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "49": {
+    "50": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,50 +1,51 @@
 {
-  "'": 24,
-  "3": 37,
-  "[PAD]": 47,
-  "[UNK]": 46,
-  "a": 33,
-  "b": 17,
-  "c": 12,
-  "d": 4,
-  "e": 11,
-  "f": 34,
-  "g": 9,
-  "h": 42,
-  "i": 31,
-  "j": 6,
-  "k": 44,
-  "l": 14,
-  "m": 27,
-  "n": 2,
-  "o": 23,
-  "p": 35,
-  "q": 3,
-  "r": 7,
-  "s": 18,
-  "t": 13,
-  "u": 16,
-  "v": 28,
-  "w": 15,
-  "x": 43,
-  "y": 0,
-  "z": 26,
-  "|": 8,
-  "à": 21,
-  "á": 5,
-  "â": 20,
-  "ã": 22,
-  "ç": 41,
-  "è": 32,
-  "é": 36,
-  "ê": 25,
-  "ë": 40,
-  "ñ": 29,
-  "ô": 19,
-  "ö": 10,
-  "ø": 30,
-  "ù": 1,
-  "û": 45,
-  "ü": 38,
-  "ı": 39
+  "'": 31,
+  "3": 15,
+  "X": 25,
+  "[PAD]": 48,
+  "[UNK]": 47,
+  "a": 14,
+  "b": 23,
+  "c": 5,
+  "d": 27,
+  "e": 24,
+  "f": 16,
+  "g": 29,
+  "h": 1,
+  "i": 45,
+  "j": 35,
+  "k": 9,
+  "l": 36,
+  "m": 22,
+  "n": 42,
+  "o": 17,
+  "p": 21,
+  "q": 28,
+  "r": 10,
+  "s": 46,
+  "t": 37,
+  "u": 0,
+  "v": 34,
+  "w": 12,
+  "x": 8,
+  "y": 43,
+  "z": 33,
+  "|": 26,
+  "à": 11,
+  "á": 19,
+  "â": 39,
+  "ã": 30,
+  "ç": 40,
+  "è": 38,
+  "é": 32,
+  "ê": 4,
+  "ë": 41,
+  "ñ": 13,
+  "ô": 18,
+  "ö": 3,
+  "ø": 7,
+  "ù": 44,
+  "û": 6,
+  "ü": 2,
+  "ı": 20
 }