o i1@s~ddlmZmZddlZddlZ     ddeeefdeejd ed ed e d ed ede dede dedej fddZ dS))OptionalTupleNstaticFTshape padding_mask mask_prob mask_length mask_type mask_other min_masks no_overlap min_spacerequire_same_masks mask_dropoutreturnc  s&|\} } t| | fd} t|| t|tj}t||}g}t| D]}|durN| || }t||t|tj}t||}n| }|}|dkr]t||nA|dkrotjj ||dd|dn/|dkrtjj |||dd d Dn|d krtjj ||dd d Dntd |t dkrt||dd<|r gfdd}d|fg}t}tddD]>tfdd|Dtj}t |}|dkrn#|t |}tjjt||d}||\}}|||||qtn-t}|||kr||d}tjj|||ddtfdd ttD|t|kq&tdd |D}t|D]<\}t|krk| rktjj|dd| dkrtt| t}tjjt|ddd| |f<qT| S)a Computes random mask spans for a given shape Args: shape: the the shape for which to compute masks. should be of size 2 where first element is batch size and 2nd is timesteps padding_mask: optional padding mask of the same size as shape, which will prevent masking padded elements mask_prob: probability for each token to be chosen as start of the span to be masked. this will be multiplied by number of timesteps divided by length of mask span to mask approximately this percentage of all elements. however due to overlaps, the actual number will be smaller (unless no_overlap is True) mask_type: how to compute mask lengths static = fixed size uniform = sample from uniform distribution [mask_other, mask_length*2] normal = sample from normal distribution with mean mask_length and stdev mask_other. mask is min 1 element poisson = sample from possion distribution with lambda = mask length min_masks: minimum number of masked spans no_overlap: if false, will switch to an alternative recursive algorithm that prevents spans from overlapping min_space: only used if no_overlap is True, this is how many elements to keep unmasked between spans require_same_masks: if true, will randomly drop out masks until same amount of masks remains in each sample mask_dropout: randomly dropout this percentage of masks in each example FNruniform)sizenormalcSsg|] }tdtt|qS)r)maxintround.0xrU/home/ubuntu/.local/lib/python3.10/site-packages/funasr/models/data2vec/data_utils.py Osz(compute_mask_indices..poissoncSsg|]}tt|qSr)rrrrrrrRszunknown mask selection rcstj|||fddt|Dg}||kr,||df|||krA|||f|S)Nc3s|]}|VqdS)Nr)ri span_startrr ^sz8compute_mask_indices..arrange..r)nprandomrandintextendrangeappend)selength keep_length new_parts)mask_idcrr"rarrange\sz%compute_mask_indices..arrangeT)reversec3s0|]\}}||kr||ndVqdS)rNr)rr+r,)r-rrrr$ks.z'compute_mask_indices..)p)replacecs*g|]}t|D]}||q qSr)r))rjoffset)lengthsr0rrr~s*cSsg|]}t|qSr)len)rmrrrrs)r%fullrfloatr&randrr)longsumitemr'rr Exceptionminsortedfromiterint32choicer8popr(asarrayr*unique enumeraterintastype)rrrr r r r r rrrbszall_szmask all_num_mask mask_idcsr!sznum_maskr1parts min_lengthlensl_sumprobscr+r,min_len num_holesr)r-r7r0rrcompute_mask_indices s#         r[)rrrFrTr) typingrrnumpyr%torchrTensorr;strboolndarrayr[rrrrsF