o 2wii@sddlmZddlZddlmZddlmZddlmZej e dddej d ej dd d d ej d e d ej ddedddgddej ddedddgddej dd ddej dddedd d!ed"eed#eed$ed%ed&ef d'd(ZdS)))ListN)prepareprepare_fisher_english)PathlikeT) show_default)context_settingsz corpus-dirF)exists file_okay)typez output-dirz-adz --audio-dirs LDC2004S13 LDC2005S13z_Audio dirs, e.g., `LDC2004S13 LDC2005S13`. Multiple corpora can be provided by repeating `-ad`.)r multipledefaulthelpz-tdz--transcript-dirs LDC2004T19 LDC2005T19zdTranscript dirs, e.g., `LDC2004T19 LDC2005T19`. Multiple corpora can be provided by repeating `-ad`.z--absolute-pathszPWhether to return absolute or relative (to the corpus dir) paths for recordings.)rrz-jz --num-jobsz8Number of concurrent processes scanning the audio files.)rr r corpus_dir audio_dirstranscript_dirs output_dirabsolute_pathsnum_jobscCst||||||ddS)ae The Fisher English Part 1, 2 corpus preparation.  This is conversational telephone speech collected as 2-channel, 8kHz-sampled data. The catalog number LDC2004S13 and LDC2005S13 for audio corpora and LDC2004T19 LDC2005T19 for transcripts. This data is not available for free - your institution needs to have an LDC subscription. rrrrrrNrrrd/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/lhotse/bin/modes/recipes/fisher_english.pyfisher_english s0 r)typingrclicklhotse.bin.modesrlhotse.recipesr lhotse.utilsrcommanddictargumentPathoptionstrintboolrrrrrsb