csikasote
/

wav2vec2-large-mms-1b-bemba-colab

Automatic Speech Recognition

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

csikasote commited on Jul 14, 2023

Commit

1b5fd69

•

1 Parent(s): 76b34db

Upload tokenizer

Files changed (2) hide show

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

tokenizer_config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
-  "target_lang": "bemba",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

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

vocab.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "bemba": {
     "[PAD]": 28,
     "[UNK]": 27,
     "a": 1,

 {
+  "bem": {
     "[PAD]": 28,
     "[UNK]": 27,
     "a": 1,