behroz
/

sp_proj

Automatic Speech Recognition

Transformers

PyTorch

TensorBoard

wav2vec2

Generated from Trainer

Model card Files Files and versions

xet

Metrics Training metrics Community

sp_proj / tokenizer_config.json

behroz

add tokenizer

7e0ac9e almost 4 years ago

raw

history blame contribute delete

181 Bytes

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