Batch inference

[LiuZH-19]

Hi,
I would like to inquire about performing batch inference using XCodec. Specifically, what is the expected shape of the wav input in the following code snippet ? Should the wav input be of shape [batch_size, 1, num_samples]?

    compressed = soundstream.encode(wav,   target_bw=args.bw)
    print(f"Compressed shape: {compressed.shape}")
    # Decode and save
    out = soundstream.decode(compressed)
    out = out.detach().cpu().squeeze(0)

Any clarification or examples would be greatly appreciated.

Thank you!