iddlmZddlmZmZmZddlmZmZddl m Z m Z ddl m Z ddlmZddlmZmZesdgZGd d e Zy ) )Sequence)AnyOptionalUnion)Tensortensor) _wip_compute _wip_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzWordInfoPreserved.plotceZdZUdZdZeed<dZeed<dZeed<dZ e ed<dZ e ed <e ed <e ed <e ed <d e ddffd ZdeeeefdeeeefddfdZde fdZ ddeee ee fdeedefdZxZS)WordInfoPreservedaWord Information Preserved (`WIP`_) is a metric of the performance of an automatic speech recognition system. This value indicates the percentage of words that were correctly predicted between a set of ground- truth sentences and a set of hypothesis sentences. The higher the value, the better the performance of the ASR system with a WordInfoPreserved of 1 being a perfect score. Word Information Preserved rate can then be computed as: .. math:: wip = \frac{C}{N} * \frac{C}{P} where: - :math:`C` is the number of correct words, - :math:`N` is the number of words in the reference - :math:`P` is the number of words in the prediction As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~List`): Transcription(s) to score as a string or list of strings - ``target`` (:class:`~List`): Reference(s) for each speech input as a string or list of strings As output of ``forward`` and ``compute`` the metric returns the following output: - ``wip`` (:class:`~torch.Tensor`): A tensor with the Word Information Preserved score Args: kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Examples: >>> from torchmetrics.text import WordInfoPreserved >>> preds = ["this is the prediction", "there is an other sample"] >>> target = ["this is the reference", "there is another one"] >>> wip = WordInfoPreserved() >>> wip(preds, target) tensor(0.3472) Fis_differentiablehigher_is_betterfull_state_updateplot_lower_boundg?plot_upper_bounderrors preds_total target_totalkwargsreturnNc t|di||jdtdd|jdtdd|jdtddy)Nrrsum)dist_reduce_fxrr)super__init__ add_stater)selfr __class__s j/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/text/wip.pyr!zWordInfoPreserved.__init__MsW "6" xUC ~vc{5I }fSk%Hpredstargetct||\}}}|xj|z c_|xj|z c_|xj|z c_y)z*Update state with predictions and targets.N)r rrr)r#r'r(rrrs r%updatezWordInfoPreserved.updateVsE,7v,F) k v  \) K'r&cXt|j|j|jS)z)Calculate the Word Information Preserved.)r rrr)r#s r%computezWordInfoPreserved.compute]s!DKK):):D>> # Example plotting a single value >>> from torchmetrics.text import WordInfoPreserved >>> metric = WordInfoPreserved() >>> preds = ["this is the prediction", "there is an other sample"] >>> target = ["this is the reference", "there is another one"] >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torchmetrics.text import WordInfoPreserved >>> metric = WordInfoPreserved() >>> preds = ["this is the prediction", "there is an other sample"] >>> target = ["this is the reference", "there is another one"] >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )_plot)r#r-r.s r%plotzWordInfoPreserved.plotasTzz#r""r&)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrr!rstrlistr*r,rrr rr1 __classcell__)r$s@r%rrs$L$t#"d"#t#!e!!e! NII I(E#tCy.1(5d3i;P(UY(NN _c*#E&(6*:":;<*#IQRZI[*# *#r&rN)collections.abcrtypingrrrtorchrr torchmetrics.functional.text.wipr r torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r__doctest_skip__rrr&r%rDs9%'' F&@@01o#o#r&