speecht5_finetuned_voxpopuli_nl / tokenizer_config.json
MariaK's picture
Training in progress, step 1000
4daa189
raw
history blame
294 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_max_length": 600,
"normalize": false,
"pad_token": "<pad>",
"processor_class": "SpeechT5Processor",
"sp_model_kwargs": {},
"tokenizer_class": "SpeechT5Tokenizer",
"unk_token": "<unk>"
}