mspeecht5_asr / tokenizer_config.json
ambujm22's picture
Training in progress, step 500
2fdee27
raw
history blame contribute delete
272 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_max_length": 450,
"pad_token": "<pad>",
"processor_class": "SpeechT5Processor",
"sp_model_kwargs": {},
"tokenizer_class": "SpeechT5Tokenizer",
"unk_token": "<unk>"
}