moro23
/

wav2vec-large-xls-r-300-ha-colab_4

Automatic Speech Recognition

Transformers

PyTorch

wav2vec2

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

wav2vec-large-xls-r-300-ha-colab_4 / tokenizer_config.json

moro23

add tokenizer

e79dc58 over 2 years ago

raw

history blame

181 Bytes

{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}