iddlmZddlmZmZmZddlmZmZddl m Z ddl m Z ddl mZmZmZddlmZmZdd d giZesd gZGd de Zy ))Sequence)AnyOptionalUnion)Tensortensor)'non_intrusive_speech_quality_assessment)Metric)_LIBROSA_AVAILABLE_MATPLOTLIB_AVAILABLE_REQUESTS_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE#NonIntrusiveSpeechQualityAssessmentlibrosarequestsz(NonIntrusiveSpeechQualityAssessment.plotceZdZUdZeed<eed<dZeed<dZeed<dZ eed<d Z e ed <d Z e ed <d e deddffd ZdeddfdZdefdZddeeeedfdeedefdZxZS)ruJ`Non-Intrusive Speech Quality Assessment`_ (NISQA v2.0) [1], [2]. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): float tensor with shape ``(...,time)`` As output of ``forward`` and ``compute`` the metric returns the following output - ``nisqa`` (:class:`~torch.Tensor`): float tensor reduced across the batch with shape ``(5,)`` corresponding to overall MOS, noisiness, discontinuity, coloration and loudness in that order .. hint:: Using this metric requires you to have ``librosa`` and ``requests`` installed. Install as ``pip install librosa requests``. .. caution:: The ``forward`` and ``compute`` methods in this class return values reduced across the batch. To obtain values for each sample, you may use the functional counterpart :func:`~torchmetrics.functional.audio.nisqa.non_intrusive_speech_quality_assessment`. Args: fs: sampling frequency of input Raises: ModuleNotFoundError: If ``librosa`` or ``requests`` are not installed Example: >>> import torch >>> from torchmetrics.audio import NonIntrusiveSpeechQualityAssessment >>> _ = torch.manual_seed(42) >>> preds = torch.randn(16000) >>> nisqa = NonIntrusiveSpeechQualityAssessment(16000) >>> nisqa(preds) tensor([1.0433, 1.9545, 2.6087, 1.3460, 1.7117]) References: - [1] G. Mittag and S. Möller, "Non-intrusive speech quality assessment for super-wideband speech communication networks", in Proc. ICASSP, 2019. - [2] G. Mittag, B. Naderi, A. Chehadi and S. Möller, "NISQA: A deep CNN-self-attention model for multidimensional speech quality prediction with crowdsourced datasets", in Proc. INTERSPEECH, 2021. sum_nisqatotalFfull_state_updateis_differentiableThigher_is_betterplot_lower_boundg@plot_upper_boundfskwargsreturnNc t|d i|trts t dt |t r|dkrtd|||_|jdtgdd|jdtddy) NziNISQA metric requires that librosa and requests are installed. Install as `pip install librosa requests`.rz9Argument `fs` expected to be a positive integer, but got r)rrrrrsum)defaultdist_reduce_fxr) super__init__r r ModuleNotFoundError isinstanceint ValueErrorr add_stater)selfrr __class__s m/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/audio/nisqa.pyr%z,NonIntrusiveSpeechQualityAssessment.__init__Xs "6"!)<%= "c"bAgXY[X\]^ ^ {F3L,M^cd wq %Hpredsc(t||jj|jj}|j dd}|xj|j dz c_|xj|jdz c_y)zUpdate state with predictions.r)dimN) r rtordevicereshaper rshape)r+r/ nisqa_batchs r-updatez*NonIntrusiveSpeechQualityAssessment.updatefsu=  GG  "T^^ " " #  "))"a0  +//a/00 k''** r.c4|j|jz S)zCompute metric.)rr)r+s r-computez+NonIntrusiveSpeechQualityAssessment.computeqs~~ **r.valaxc&|j||S)aFPlot a single or multiple values from the metric. Args: val: Either a single result from calling ``metric.forward`` or ``metric.compute`` or a list of these results. If no value is provided, will automatically call ``metric.compute`` and plot that result. ax: A matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If ``matplotlib`` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.audio import NonIntrusiveSpeechQualityAssessment >>> metric = NonIntrusiveSpeechQualityAssessment(16000) >>> metric.update(torch.randn(16000)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.audio import NonIntrusiveSpeechQualityAssessment >>> metric = NonIntrusiveSpeechQualityAssessment(16000) >>> values = [] >>> for _ in range(10): ... values.append(metric(torch.randn(16000))) >>> fig_, ax_ = metric.plot(values) )_plot)r+r<r=s r-plotz(NonIntrusiveSpeechQualityAssessment.plotusLzz#r""r.)NN)__name__ __module__ __qualname____doc__r__annotations__rboolrrrfloatrr(rr%r9r;rrrrrr@ __classcell__)r,s@r-rr#s*X M#t##t#!d!!e!!e! I3 I# I$ I +F +t +++&#fhv&6<=&#(S[J\&#hv&#r.N)collections.abcrtypingrrrtorchrr#torchmetrics.functional.audio.nisqar torchmetrics.metricr torchmetrics.utilities.importsr r r torchmetrics.utilities.plotrr__doctest_requires____doctest_skip__rr#r.r-rRsS%'' W& A= :?VWBCx#&x#r.