Token indices sequence length is longer than the specified maximum sequence length for this model (153482 > 131072). Running this sequence through the model will result in indexing errors
Author: tianleiwang254-debugCreated Apr 10, 2026Updated Jul 14, 2026
Why is it that my audio file, which is only 34 minutes long, exceeds the maximum sequence length? I conducted the test using Python inference.
Source: microsoft/VibeVoice