zlm_b64_le4_s4000 / checkpoint-500 /tokenizer_config.json
mikhail-panzo's picture
Training in progress, step 500, checkpoint
46b8e47 verified
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"79": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"80": {
"content": "<ctc_blank>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 600,
"normalize": false,
"pad_token": "<pad>",
"processor_class": "SpeechT5Processor",
"sp_model_kwargs": {},
"tokenizer_class": "SpeechT5Tokenizer",
"unk_token": "<unk>"
}