marian-finetuned-iitb-en-to-hi-v2 / tokenizer_config.json

Training in progress epoch 0

ae06b3b 7 months ago

No virus

282 Bytes

	{
	"clean_up_tokenization_spaces": true,
	"eos_token": "</s>",
	"model_max_length": 512,
	"pad_token": "<pad>",
	"separate_vocabs": false,
	"source_lang": "eng",
	"sp_model_kwargs": {},
	"target_lang": "hin",
	"tokenizer_class": "MarianTokenizer",
	"unk_token": "<unk>"
	}