obokkkk
/

hubert-large-ls960-ft-timit

Automatic Speech Recognition

Transformers

PyTorch

TensorBoard

hubert

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

hubert-large-ls960-ft-timit / tokenizer_config.json

obokkkk

add tokenizer

c991a53 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"}