Mayer_yan

我遇到这个问题，加载模型的权重和代码中定义的网络结构不匹配，请问怎么改？

12

/data/AI_big_model/GeneFacePlusPlus-main/GeneFacePlusPlus-main/tasks/radnerfs/dataset_utils.py:266: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor). self.lm68s = torch.tensor(self.lm2ds[:, index_lm68_from_lm478, :]) val: Smooth head trajectory (rotation and...

调用代码： sets = cfg.parse_ini() print("===================================") model = WhisperModel(model, device=sets.get('devtype'), compute_type=sets.get('cuda_com_type')) segments, _ = model.transcribe(audio_array, beam_size=sets.get('beam_size'), best_of=sets.get('best_of'), temperature=0 if sets.get('temperature') == 0 else [0.0, 0.2, 0.4, 0.6, 0.8, 1.0], condition_on_previous_text=sets.get('condition_on_previous_text'), vad_filter=sets.get('vad'),...