cdactvm
/

w2v-bert-kannada_new

Automatic Speech Recognition

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

cdactvm commited on Dec 17, 2024

Commit

4681f8f

·

verified ·

1 Parent(s): a12ad7e

Upload tokenizer

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +4 -5
vocab.json +5 -8

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 95,
-  "<s>": 94
 }

 {
+  "</s>": 92,
+  "<s>": 91
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "92": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "93": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "94": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "95": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -39,7 +39,6 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

 {
   "added_tokens_decoder": {
+    "89": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "90": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "91": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "92": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json CHANGED Viewed

@@ -12,8 +12,8 @@
   "9": 11,
   "I": 12,
   "U": 13,
-  "[PAD]": 93,
-  "[UNK]": 92,
   "_": 14,
   "|": 0,
   "ಂ": 15,
@@ -87,10 +87,7 @@
   "೩": 83,
   "೪": 84,
   "೫": 85,
-  "೬": 86,
-  "೭": 87,
-  "೮": 88,
-  "೯": 89,
-  "": 90,
-  "‍": 91
 }

   "9": 11,
   "I": 12,
   "U": 13,
+  "[PAD]": 90,
+  "[UNK]": 89,
   "_": 14,
   "|": 0,
   "ಂ": 15,
   "೩": 83,
   "೪": 84,
   "೫": 85,
+  "೮": 86,
+  "": 87,
+  "‍": 88
 }