speecht5_voxpopuli_sl / tokenizer_config.json

Training in progress, step 1000

5e60042 about 3 years ago

272 Bytes

{
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "model_max_length": 600,
  "pad_token": "<pad>",
  "processor_class": "SpeechT5Processor",
  "sp_model_kwargs": {},
  "tokenizer_class": "SpeechT5Tokenizer",
  "unk_token": "<unk>"
}

	{
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "</s>",
	"model_max_length": 600,
	"pad_token": "<pad>",
	"processor_class": "SpeechT5Processor",
	"sp_model_kwargs": {},
	"tokenizer_class": "SpeechT5Tokenizer",
	"unk_token": "<unk>"
	}