bridge.models.minicpmo.audio#
Adapt current Whisper attention to MiniCPM-o’s offline encoder contract.
Module Contents#
Classes#
Keep HF attention math and parameter names with a legacy return tuple. |
API#
- class bridge.models.minicpmo.audio.MiniCPMOAudioAttention#
Bases:
transformers.models.whisper.modeling_whisper.WhisperAttentionKeep HF attention math and parameter names with a legacy return tuple.
MiniCPM-o 4.5’s encoder layer unpacks three values, whereas current HF Whisper returns two. Offline understanding does not consume a KV cache.
- forward(
- hidden_states: torch.Tensor,
- *,
- past_key_value: Any = None,
- past_key_values: Any = None,
- layer_head_mask: torch.Tensor | None = None,
- **kwargs: Any,
Return the native attention outputs plus an unused cache slot.