oskarandrsson
/

wav2vec2-2-bert-swedish-lm

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

oskarandrsson commited on May 23

Commit

8eff79b

•

1 Parent(s): 11e4086

Upload tokenizer

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +6 -7
vocab.json +6 -3

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 33,
-  "<s>": 32
 }

 {
+  "</s>": 36,
+  "<s>": 35
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "30": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "31": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,18 +16,18 @@
       "single_word": false,
       "special": false
     },
-    "32": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "33": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -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": {
+    "33": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "34": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "35": {
       "content": "<s>",
       "lstrip": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "36": {
       "content": "</s>",
       "lstrip": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
   "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]": 31,
-  "[UNK]": 30,
   "a": 1,
   "b": 2,
   "c": 3,
@@ -30,5 +30,8 @@
   "|": 0,
   "ä": 27,
   "å": 28,
-  "ö": 29
 }

 {
+  "[PAD]": 34,
+  "[UNK]": 33,
   "a": 1,
   "b": 2,
   "c": 3,
   "|": 0,
   "ä": 27,
   "å": 28,
+  "é": 29,
+  "ô": 30,
+  "ö": 31,
+  "ü": 32
 }