wav2vec2-bert_Assyrian_Urmi_ASR_model / tokenizer_config.json
Selest's picture
Upload folder using huggingface_hub
3971573 verified
{
"added_tokens_decoder": {
"0": {
"content": " ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"35": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"36": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"backend": "custom",
"bos_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"is_local": true,
"local_files_only": false,
"model_max_length": 1000000000000000019884624838656,
"model_specific_special_tokens": {
"word_delimiter_token": " "
},
"pad_token": "<pad>",
"processor_class": "Wav2Vec2BertProcessor",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": " "
}