rh dZddlZddlmZddlmZmZmZddlZ ddl Z ddl Z ddl m Z ddl mZddlmZdd lmZdd lmZdd lmZdd lmZmZdd lmZddlmZmZddlm Z ejBe"Z#eedGddeZ$eedGddeZ%e jLjNdZ( d@dZ)dZ*Gdde jjVZ,Gdde jVZ-Gdd e jVZ.Gd!d"e jVZ/Gd#d$e jVZ0Gd%d&e jVZ1Gd'd(e jVZ2Gd)d*e jVZ3Gd+d,e jVZ4Gd-d.e jVZ5Gd/d0e jVZ6Gd1d2e jVZ7Gd3d4e jVZ8Gd5d6eZ9Gd7d8e jVZ:Gd9d:e jVZ;eGd;dd?e<Z=d?dy)AzPyTorch VITS model.N) dataclass)AnyOptionalUnion)nn)ACT2FN)is_deepspeed_zero3_enabled)is_fsdp_managed_module)_prepare_4d_attention_mask)GradientCheckpointingLayer)BaseModelOutput ModelOutput)PreTrainedModel)auto_docstringlogging) VitsConfigz` Describes the outputs for the VITS model, with potential hidden states and attentions. ) custom_introceZdZUdZdZeejed<dZ eejed<dZ ee ejed<dZ ee ejed<dZ ee ejed<y)VitsModelOutputa" waveform (`torch.FloatTensor` of shape `(batch_size, sequence_length)`): The final audio waveform predicted by the model. sequence_lengths (`torch.FloatTensor` of shape `(batch_size,)`): The length in samples of each element in the `waveform` batch. spectrogram (`torch.FloatTensor` of shape `(batch_size, sequence_length, num_bins)`): The log-mel spectrogram predicted at the output of the flow model. This spectrogram is passed to the Hi-Fi GAN decoder model to obtain the final audio waveform. Nwaveformsequence_lengths spectrogram hidden_states attentions)__name__ __module__ __qualname____doc__rrtorch FloatTensor__annotations__rrtuplerry/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/vits/modeling_vits.pyrr(s-1Hhu(()048hu00186:K% 1 123:8