colorlessideas
/

xls-r-300m-tenakichwa-10

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

colorlessideas commited on 15 days ago

Commit

d2e0f40

·

verified ·

1 Parent(s): 11a88fb

Upload tokenizer

Files changed (3) hide show

added_tokens.json +2 -2
tokenizer_config.json +4 -5
vocab.json +6 -7

added_tokens.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "</s>": 36,
-  "<s>": 35
 }

 {
+  "</s>": 35,
+  "<s>": 34
 }

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "33": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "34": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "35": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "36": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,6 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

 {
   "added_tokens_decoder": {
+    "32": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "33": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "34": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "35": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
   "extra_special_tokens": {},
   "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]": 34,
-  "[UNK]": 33,
   "a": 1,
   "b": 2,
   "c": 3,
@@ -24,14 +24,13 @@
   "u": 21,
   "v": 22,
   "w": 23,
-  "y": 24,
-  "z": 25,
   "|": 0,
-  "¿": 26,
   "á": 27,
   "é": 28,
   "í": 29,
   "ñ": 30,
-  "ó": 31,
-  "ú": 32
 }

 {
+  "[PAD]": 33,
+  "[UNK]": 32,
   "a": 1,
   "b": 2,
   "c": 3,
   "u": 21,
   "v": 22,
   "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
   "|": 0,
   "á": 27,
   "é": 28,
   "í": 29,
   "ñ": 30,
+  "ó": 31
 }