o yi @sddlmZmZmZddlZddlmZmZddlmZdee ee fdee ee fdeeeffdd Z d ed edefd d Z dee ee fdee ee fdefddZ dS))ListTupleUnionN)Tensortensor)_edit_distancepredstargetreturncCst|tr|g}t|tr|g}tdtjd}tdtjd}t||D]\}}|}|}|t||7}|tt |t |7}q#||fS)aUpdate the mer score with the current set of references and predictions. Args: preds: Transcription(s) to score as a string or list of strings target: Reference(s) for each speech input as a string or list of strings Returns: Number of edit operations to get from the reference to the prediction, summed over all samples Number of words overall references r)dtype) isinstancestrrtorchfloatzipsplitrmaxlen)rr errorstotalpredtgt pred_tokens tgt_tokensrT/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/text/mer.py _mer_updates  rrrcCs||S)zCompute the match error rate. Args: errors: Number of edit operations to get from the reference to the prediction, summed over all samples total: Number of words overall references Returns: Match error rate score r)rrrrr _mer_compute4s rcCst||\}}t||S)aMatch error rate is a metric of the performance of an automatic speech recognition system. This value indicates the percentage of words that were incorrectly predicted and inserted. The lower the value, the better the performance of the ASR system with a MatchErrorRate of 0 being a perfect score. Args: preds: Transcription(s) to score as a string or list of strings target: Reference(s) for each speech input as a string or list of strings Returns: Match error rate score Examples: >>> preds = ["this is the prediction", "there is an other sample"] >>> target = ["this is the reference", "there is another one"] >>> match_error_rate(preds=preds, target=target) tensor(0.4444) )rr)rr rrrrrmatch_error_rateAs  r) typingrrrrrr#torchmetrics.functional.text.helperrr rrrrrrrs&