Sajjo
/

w2v-bert-2.0-tamil-gpu-custom_preprocessed_v2

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Sajjo commited on Apr 30

Commit

9fbc72a

•

1 Parent(s): c876d66

Upload tokenizer

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +4 -5
vocab.json +4 -3

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 53,
-  "<s>": 52
 }

 {
+  "</s>": 54,
+  "<s>": 53
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "50": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "51": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "52": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "53": {
       "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": {
+    "51": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "52": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "53": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "54": {
       "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

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 51,
-  "[UNK]": 50,
   "|": 0,
   "·": 1,
   "ஃ": 2,
@@ -50,5 +50,6 @@
   "ோ": 46,
   "ௌ": 47,
   "்": 48,
-  "ௗ": 49
 }

 {
+  "[PAD]": 52,
+  "[UNK]": 51,
   "|": 0,
   "·": 1,
   "ஃ": 2,
   "ோ": 46,
   "ௌ": 47,
   "்": 48,
+  "ௗ": 49,
+  "ഥ": 50
 }