HuyenNguyen
/

wav2vec2-large-mms-1b-turkish-colab

Automatic Speech Recognition

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

HuyenNguyen commited on Nov 12, 2023

Commit

c22c4b3

·

1 Parent(s): 3f5bee9

Upload tokenizer

Files changed (2) hide show

tokenizer_config.json +1 -1
vocab.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -40,7 +40,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
-  "target_lang": "vi",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
+  "target_lang": "tur",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "vi": {
     "[PAD]": 88,
     "[UNK]": 87,
     "a": 1,

 {
+  "tur": {
     "[PAD]": 88,
     "[UNK]": 87,
     "a": 1,