luhya-asr-w2v-BERT / processor /tokenizer_config.json
Sam4rano's picture
Upload folder using huggingface_hub
53848f2 verified
Raw
History Blame Contribute Delete
1.37 kB
{
"added_tokens_decoder": {
"0": {
"content": "|",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"46": {
"content": "[UNK]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"47": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49": {
"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": "|"
}