aconeil
/

w2v-bert-2.0-zuluMDD

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

aconeil commited on 7 days ago

Commit

69e130e

·

verified ·

1 Parent(s): 1e99c64

Upload tokenizer

Files changed (3) hide show

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

added_tokens.json CHANGED Viewed

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

 {
+  "</s>": 32,
+  "<s>": 31
 }

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,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "32": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "33": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,6 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

 {
   "added_tokens_decoder": {
+    "29": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "30": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
       "single_word": false,
       "special": false
     },
+    "31": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "single_word": false,
       "special": true
     },
+    "32": {
       "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

@@ -1,7 +1,7 @@
 {
   "[": 1,
-  "[PAD]": 31,
-  "[UNK]": 30,
   "]": 2,
   "a": 3,
   "b": 4,
@@ -29,6 +29,5 @@
   "x": 26,
   "y": 27,
   "z": 28,
-  "|": 0,
-  "ạ": 29
 }

 {
   "[": 1,
+  "[PAD]": 30,
+  "[UNK]": 29,
   "]": 2,
   "a": 3,
   "b": 4,
   "x": 26,
   "y": 27,
   "z": 28,
+  "|": 0
 }