def si_sdr()

in training/eval.py [0:0]

• 20 lines of code
• 4 McCabe index (conditional complexity)

def si_sdr(audios, device, input_sampling_rate=44100):
    max_audio_length = 15 * SQUIM_OBJECTIVE.sample_rate
    model = SQUIM_OBJECTIVE.get_model().to((device))

    output_sampling_rate = SQUIM_OBJECTIVE.sample_rate
    if input_sampling_rate != output_sampling_rate:
        audios = [
            torchaudio.functional.resample(
                torch.tensor(audio)[None, :].to(device).float(), input_sampling_rate, output_sampling_rate
            )
            for audio in audios
        ]

    def apply_squim(waveform):
        with torch.no_grad():
            waveform = waveform[:, : min(max_audio_length, waveform.shape[1])]
            _, _, sdr_sample = model(waveform)
            sdr_sample = sdr_sample.cpu()[0]
        return sdr_sample

    si_sdrs = [apply_squim(audio) for audio in audios]
    audios, model = release_memory(audios, model)
    return si_sdrs