Mengkedalai
/

w2v-bert-2.0-mongolian-colab-CV16.0

Automatic Speech Recognition

Model card Files Files and versions Metrics Training metrics Community

Mengkedalai commited on Oct 28, 2024

Commit

5ce2df0

·

verified ·

1 Parent(s): 3b41a96

Upload tokenizer

Files changed (2) hide show

tokenizer_config.json +0 -1
vocab.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -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",

   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

vocab.json CHANGED Viewed

@@ -27,7 +27,7 @@
   "ц": 23,
   "ч": 24,
   "ш": 25,
-  "ъ": 26,
   "ы": 27,
   "ь": 28,
   "э": 29,

   "ц": 23,
   "ч": 24,
   "ш": 25,
+  "щ": 26,
   "ы": 27,
   "ь": 28,
   "э": 29,