lgris
/

bp500-base100k_voxpopuli

Automatic Speech Recognition

portuguese-speech-corpus

Inference Endpoints

Model card Files Files and versions Community

bp500-base100k_voxpopuli / tokenizer_config.json

lgris's picture

Update from gris

dac1a20 almost 3 years ago

181 Bytes

{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}