tiny-processor-vibevoice_asr / tokenizer_config.json
hf-transformers-bot's picture
Add tiny processor fixture for testing
9df5cd1 verified
Raw
History Blame Contribute Delete
4.86 kB
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"is_local": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"processor_class": "VibeVoiceAsrProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"500": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"501": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"502": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"503": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"504": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"505": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"506": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"507": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"508": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"509": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"510": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"511": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"512": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"513": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"514": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"515": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"516": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"517": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"518": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"519": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"520": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"521": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
}
}
}