j 0SrSSKrSSKJr "SS5rg)zPreprocessors for audioN)Resamplec.\rSrSrSrSSjrSrSrSrg) AudioNormalizeraNormalizes audio into a standard format Arguments --------- sample_rate : int The sampling rate to which the incoming signals should be converted. mix : {"avg-to-mono", "keep"} "avg-to-mono" - add all channels together and normalize by number of channels. This also removes the channel dimension, resulting in [time] format tensor. "keep" - don't normalize channel information Example ------- >>> from speechbrain.dataio import audio_io >>> example_file = ( ... "tests/samples/multi-mic/speech_-0.82918_0.55279_-0.082918.flac" ... ) >>> signal, sr = audio_io.load(example_file, channels_first=False) >>> normalizer = AudioNormalizer(sample_rate=8000) >>> normalized = normalizer(signal, sr) >>> signal.shape torch.Size([160000, 4]) >>> normalized.shape torch.Size([80000]) NOTE ---- This will also upsample audio. However, upsampling cannot produce meaningful information in the bandwidth which it adds. Generally models will not work well for upsampled data if they have not specifically been trained to do so. cRXlUS;a[SU35eX l0Ulg)N) avg-to-monokeepz Unexpected mixing configuration ) sample_rate ValueErrormix_cached_resamplers)selfr r s ګC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\speechbrain/dataio/preprocess.py__init__AudioNormalizer.__init__*s1& - -?uEF F"$cX R;a"[X R5URU'URUnU"URS55R S5nUR U5$)aPerform normalization Arguments --------- audio : torch.Tensor The input waveform torch tensor. Assuming [time, channels], or [time]. sample_rate : int Rate the audio was sampled at. Returns ------- audio : torch.Tensor Channel- and sample-rate-normalized audio. r)r rr unsqueezesqueeze_mix)raudior resampler resampleds r__call__AudioNormalizer.__call__1sm 55 53;--4D # #K 0++K8 eooa0199!< yy##rcUR5S:HnURS:Xa U(aU$[R"US5$URS:XaU$g)zHandle channel mixingrr N)dimr torchmean)rr flat_inputs rrAudioNormalizer._mixJsMYY[A% 88} $ ::eQ' ' 88v L r)r r r N)i>r) __name__ __module__ __qualname____firstlineno____doc__rrr__static_attributes__rrrrsB%$2rr)r'rspeechbrain.augment.time_domainrrr)rrr+s 4JJr