o yi @sddlZddlZddlmZddlmZddlmZmZer#ddl Z ndZ ddgiZ  dd ed ed e d e d ede defddZdS)N)Tensor)_check_same_shape)_MULTIPROCESSING_AVAILABLE_PESQ_AVAILABLE)$perceptual_evaluation_speech_qualitypesqFpredstargetfsmodekeep_same_device n_processesreturnc Csltstd|dvrtd||dvrtd|t|||jdkr@t|| | |}t |}nl| d|j d }| d|j d } trt|dkrttj|| |||d}t|}n)tj|j d d }t|j d D]} t|| | d d f|| d d f||| <qt |}| |j d d}|r||j}|S) aCalculates `Perceptual Evaluation of Speech Quality`_ (PESQ). It's a recognized industry standard for audio quality that takes into considerations characteristics such as: audio sharpness, call volume, background noise, clipping, audio interference ect. PESQ returns a score between -0.5 and 4.5 with the higher scores indicating a better quality. This metric is a wrapper for the `pesq package`_. Note that input will be moved to `cpu` to perform the metric calculation. .. note:: using this metrics requires you to have ``pesq`` install. Either install as ``pip install torchmetrics[audio]`` or ``pip install pesq``. Note that ``pesq`` will compile with your currently installed version of numpy, meaning that if you upgrade numpy at some point in the future you will most likely have to reinstall ``pesq``. Args: preds: float tensor with shape ``(...,time)`` target: float tensor with shape ``(...,time)`` fs: sampling frequency, should be 16000 or 8000 (Hz) mode: ``'wb'`` (wide-band) or ``'nb'`` (narrow-band) keep_same_device: whether to move the pesq value to the device of preds n_processes: integer specifiying the number of processes to run in parallel for the metric calculation. Only applies to batches of data and if ``multiprocessing`` package is installed. Returns: Float tensor with shape ``(...,)`` of PESQ values per sample Raises: ModuleNotFoundError: If ``pesq`` package is not installed ValueError: If ``fs`` is not either ``8000`` or ``16000`` ValueError: If ``mode`` is not either ``"wb"`` or ``"nb"`` RuntimeError: If ``preds`` and ``target`` do not have the same shape Example: >>> from torchmetrics.functional.audio.pesq import perceptual_evaluation_speech_quality >>> import torch >>> g = torch.manual_seed(1) >>> preds = torch.randn(8000) >>> target = torch.randn(8000) >>> perceptual_evaluation_speech_quality(preds, target, 8000, 'nb') tensor(2.2076) >>> perceptual_evaluation_speech_quality(preds, target, 16000, 'wb') tensor(1.7359) zwPESQ metric requires that pesq is installed. Either install as `pip install torchmetrics[audio]` or `pip install pesq`.)i@i>z:Expected argument `fs` to either be 8000 or 16000 but got )wbnbz;Expected argument `mode` to either be 'wb' or 'nb' but got r) n_processorr)shapeN)rModuleNotFoundError ValueErrorrndim pesq_backendrdetachcpunumpytorchtensorreshaperr pesq_batchnparrayemptyrange from_numpytodevice) r r r r r r pesq_val_nppesq_valpreds_np target_npbr,V/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/audio/pesq.pyrs26  (   .  r)Fr)rr rrtorchmetrics.utilities.checksrtorchmetrics.utilities.importsrrrr__doctest_requires__intstrboolrr,r,r,r-s4