GinobiLi
> ``` model = models[0].cuda() TTSHubInterface.update_cfg_with_data_cfg(cfg, task.data_cfg) generator = task.build_generator([model], cfg) # next(model.parameters()).device sample = TTSHubInterface.get_model_input(task, text) sample["net_input"]["src_tokens"] = sample["net_input"]["src_tokens"].cuda() sample["net_input"]["src_lengths"] = sample["net_input"]["src_lengths"].cuda() sample["speaker"] = sample["speaker"].cuda() wav, rate = TTSHubInterface.get_prediction(task,...
``` ValueError: Must flatten tensors with uniform dtype but got torch.float32 and torch.float16 ```