INNER CODE UNIT · Python

blocksize

voicepaw/so-vits-svc-fork · src/so_vits_svc_fork/inference/main.py:243

            blocksize=int(block_seconds * svc_model.target_sample),
            latency="low",
        ) as stream:
            LOG.info(f"Latency: {stream.latency}")
            while True:
                sd.sleep(1000)
    finally:
        # del model, svc_model
        torch.cuda.empty_cache()

View source record →