HuyenNguyen
/

wav2vec2-large-mms-1b-turkish-colab

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

HuyenNguyen commited on Nov 22, 2023

Commit

0e85029

·

1 Parent(s): ef83302

Upload tokenizer

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +4 -4
vocab.json +34 -36

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 92,
-  "<s>": 91
 }

 {
+  "</s>": 90,
+  "<s>": 89
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "89": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "90": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "91": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "92": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

 {
   "added_tokens_decoder": {
+    "87": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "88": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "89": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
       "single_word": false,
       "special": true
     },
+    "90": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

vocab.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "vi": {
-    "[PAD]": 90,
-    "[UNK]": 89,
     "a": 1,
     "b": 2,
     "c": 3,
@@ -57,39 +57,37 @@
     "ắ": 52,
     "ằ": 53,
     "ẳ": 54,
-    "ẵ": 55,
-    "ặ": 56,
-    "ẹ": 57,
-    "ẻ": 58,
-    "ẽ": 59,
-    "ế": 60,
-    "ề": 61,
-    "ể": 62,
-    "ễ": 63,
-    "ệ": 64,
-    "ỉ": 65,
-    "ị": 66,
-    "ọ": 67,
-    "ỏ": 68,
-    "ố": 69,
-    "ồ": 70,
-    "ổ": 71,
-    "ỗ": 72,
-    "ộ": 73,
-    "ớ": 74,
-    "ờ": 75,
-    "ở": 76,
-    "ỡ": 77,
-    "ợ": 78,
-    "ụ": 79,
-    "ủ": 80,
-    "ứ": 81,
-    "ừ": 82,
-    "ử": 83,
-    "ữ": 84,
-    "ự": 85,
-    "ỳ": 86,
-    "ỷ": 87,
-    "ỹ": 88
   }
 }

 {
   "vi": {
+    "[PAD]": 88,
+    "[UNK]": 87,
     "a": 1,
     "b": 2,
     "c": 3,
     "ắ": 52,
     "ằ": 53,
     "ẳ": 54,
+    "ặ": 55,
+    "ẹ": 56,
+    "ẻ": 57,
+    "ẽ": 58,
+    "ế": 59,
+    "ề": 60,
+    "ể": 61,
+    "ễ": 62,
+    "ệ": 63,
+    "ỉ": 64,
+    "ị": 65,
+    "ọ": 66,
+    "ỏ": 67,
+    "ố": 68,
+    "ồ": 69,
+    "ổ": 70,
+    "ỗ": 71,
+    "ộ": 72,
+    "ớ": 73,
+    "ờ": 74,
+    "ở": 75,
+    "ỡ": 76,
+    "ợ": 77,
+    "ụ": 78,
+    "ủ": 79,
+    "ứ": 80,
+    "ừ": 81,
+    "ử": 82,
+    "ữ": 83,
+    "ự": 84,
+    "ỳ": 85,
+    "ỷ": 86
   }
 }