Thienpkae
/

wav2vec2-large-xls-r-vi-colab

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Thienpkae commited on Jun 30

Commit

1dc4b9d

•

1 Parent(s): 337557b

Upload tokenizer

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +4 -4
vocab.json +35 -37

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 96,
-  "<s>": 95
 }

 {
+  "</s>": 94,
+  "<s>": 93
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "93": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "94": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "95": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "96": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

 {
   "added_tokens_decoder": {
+    "91": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "92": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "93": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "94": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 94,
-  "[UNK]": 93,
   "a": 1,
   "b": 2,
   "c": 3,
@@ -59,39 +59,37 @@
   "ậ": 55,
   "ắ": 56,
   "ằ": 57,
-  "ẳ": 58,
-  "ẵ": 59,
-  "ặ": 60,
-  "ẹ": 61,
-  "ẻ": 62,
-  "ẽ": 63,
-  "ế": 64,
-  "ề": 65,
-  "ể": 66,
-  "ễ": 67,
-  "ệ": 68,
-  "ỉ": 69,
-  "ị": 70,
-  "ọ": 71,
-  "ỏ": 72,
-  "ố": 73,
-  "ồ": 74,
-  "ổ": 75,
-  "ỗ": 76,
-  "ộ": 77,
-  "ớ": 78,
-  "ờ": 79,
-  "ở": 80,
-  "ỡ": 81,
-  "ợ": 82,
-  "ụ": 83,
-  "ủ": 84,
-  "ứ": 85,
-  "ừ": 86,
-  "ử": 87,
-  "ữ": 88,
-  "ự": 89,
-  "ỳ": 90,
-  "ỵ": 91,
-  "ỹ": 92
 }

 {
+  "[PAD]": 92,
+  "[UNK]": 91,
   "a": 1,
   "b": 2,
   "c": 3,
   "ậ": 55,
   "ắ": 56,
   "ằ": 57,
+  "ặ": 58,
+  "ẹ": 59,
+  "ẻ": 60,
+  "ẽ": 61,
+  "ế": 62,
+  "ề": 63,
+  "ể": 64,
+  "ễ": 65,
+  "ệ": 66,
+  "ỉ": 67,
+  "ị": 68,
+  "ọ": 69,
+  "ỏ": 70,
+  "ố": 71,
+  "ồ": 72,
+  "ổ": 73,
+  "ỗ": 74,
+  "ộ": 75,
+  "ớ": 76,
+  "ờ": 77,
+  "ở": 78,
+  "ỡ": 79,
+  "ợ": 80,
+  "ụ": 81,
+  "ủ": 82,
+  "ứ": 83,
+  "ừ": 84,
+  "ử": 85,
+  "ữ": 86,
+  "ự": 87,
+  "ỳ": 88,
+  "ỵ": 89,
+  "ỹ": 90
 }