Roxysun
/

cs2fi_wav2vec2-large-xls-r-300m-czech-colab

Automatic Speech Recognition

Generated from Trainer

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

cs2fi_wav2vec2-large-xls-r-300m-czech-colab / tokenizer_config.json

Roxysun's picture

Upload tokenizer

b8a20e2 over 2 years ago

1.05 kB

	{
	"added_tokens_decoder": {
	"31": {
	"content": "[UNK]",
	"lstrip": true,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": false
	},
	"32": {
	"content": "[PAD]",
	"lstrip": true,
	"normalized": false,
	"rstrip": true,
	"single_word": false,
	"special": false
	},
	"33": {
	"content": "<s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"34": {
	"content": "</s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"do_lower_case": false,
	"eos_token": "</s>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "[PAD]",
	"replace_word_delimiter_char": " ",
	"target_lang": null,
	"tokenizer_class": "Wav2Vec2CTCTokenizer",
	"unk_token": "[UNK]",
	"word_delimiter_token": "\|"
	}