Upload tokenizer

README.md

@@ -1,17 +1,17 @@
 ---
+language:
+- la
 license: mit
-base_model: facebook/w2v-bert-2.0
 tags:
 - generated_from_trainer
+datasets:
+- thiagolira/LatinYoutube
 metrics:
 - wer
+base_model: facebook/w2v-bert-2.0
 model-index:
 - name: CiceroASR
   results: []
-datasets:
-- thiagolira/LatinYoutube
-language:
-- la
 ---
 
 

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 28,
-  "<s>": 27
+  "</s>": 30,
+  "<s>": 29
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "25": {
+    "27": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "26": {
+    "28": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "27": {
+    "29": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "28": {
+    "30": {
       "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",

vocab.json

@@ -1,6 +1,6 @@
 {
-  "[PAD]": 26,
-  "[UNK]": 25,
+  "[PAD]": 28,
+  "[UNK]": 27,
   "a": 1,
   "b": 2,
   "c": 3,
@@ -23,7 +23,9 @@
   "t": 20,
   "u": 21,
   "v": 22,
-  "x": 23,
-  "y": 24,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
   "|": 0
 }