o j@sNdZddlZddlmZddlmZddlmZddZedkr%edSdS) z+Find all the unique characters in a datasetN)RawTextHelpFormatter) load_config)load_tts_samplesc Cstjdtd}|jdtddd|}t|j}t|j d|j |j d\}}||}d d d |D}t |}td d |}d d|D} t | } tdt|tdd t|tdd t|tdd t| dS)NzFind all the unique characters or phonemes in a dataset. Example runs: python TTS/bin/find_unique_chars.py --config_path config.json ) descriptionformatter_classz --config_pathzPath to dataset config file.T)typehelprequired) eval_spliteval_split_max_sizeeval_split_sizecss|]}|dVqdS)textN).0itemrrL/home/kuhnn/.local/lib/python3.10/site-packages/TTS/bin/find_unique_chars.py szmain..cSs|S)N)islower)crrr"szmain..cSsg|]}|qSr)lower)rrrrr #szmain..z > Number of unique characters: z > Unique characters: z > Unique lower characters: z* > Unique all forced to lower characters: )argparseArgumentParserr add_argumentstr parse_argsr config_pathrdatasetsr r joinsetfilterprintlensorted) parserargsr train_items eval_itemsitemstextschars lower_charschars_force_lowerrrrmain s(   r/__main__) __doc__rr TTS.configrTTS.tts.datasetsrr/__name__rrrrs   #