tbkazakova
/

wav2vec-bert-2.0-even-pakendorf

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

tbkazakova commited on Jun 4

Commit

585f1e7

•

1 Parent(s): 20b1d4e

Upload tokenizer

Files changed (3) hide show

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

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 39,
-  "<s>": 38
 }

 {
+  "</s>": 37,
+  "<s>": 36
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "36": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "37": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "38": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "39": {
       "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": {
+    "34": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "35": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "36": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "37": {
       "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]": 37,
-  "[UNK]": 36,
   "|": 0,
   "а": 1,
   "б": 2,
@@ -34,7 +34,5 @@
   "ю": 30,
   "я": 31,
   "ё": 32,
-  "ӈ": 33,
-  "ө": 34,
-  "ӫ": 35
 }

 {
+  "[PAD]": 35,
+  "[UNK]": 34,
   "|": 0,
   "а": 1,
   "б": 2,
   "ю": 30,
   "я": 31,
   "ё": 32,
+  "ӈ": 33
 }