tts/modules/wavvae/decoder/diag_gaussian.py

# Copyright 2025 ByteDance and/or its affiliates.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import torch
import numpy as np

class DiagonalGaussianDistribution(object):
    def __init__(self, parameters: torch.Tensor, deterministic: bool = False):
        self.parameters = parameters
        self.mean, self.logvar = torch.chunk(parameters, 2, dim=1)
        self.logvar = torch.clamp(self.logvar, -30.0, 20.0)
        self.deterministic = deterministic
        self.std = torch.exp(0.5 * self.logvar)
        self.var = torch.exp(self.logvar)
        if self.deterministic:
            self.var = self.std = torch.zeros_like(
                self.mean, device=self.parameters.device, dtype=self.parameters.dtype
            )

    def sample(self, generator=None) -> torch.Tensor:
        # make sure sample is on the same device as the parameters and has same dtype
        sample = torch.randn(
            self.mean.shape,
            generator=generator,
            device=self.parameters.device,
            dtype=self.parameters.dtype,
        )
        x = self.mean + self.std * sample
        return x

    def kl(self, other: "DiagonalGaussianDistribution" = None) -> torch.Tensor:
        if self.deterministic:
            return torch.Tensor([0.0])
        else:
            if other is None:
                return 0.5 * torch.pow(self.mean, 2) + self.var - 1.0 - self.logvar
            else:
                return 0.5 * (
                    torch.pow(self.mean - other.mean, 2) / other.var
                    + self.var / other.var
                    - 1.0
                    - self.logvar
                    + other.logvar
                )

    def nll(self, sample, dims) -> torch.Tensor:
        if self.deterministic:
            return torch.Tensor([0.0])
        logtwopi = np.log(2.0 * np.pi)
        return 0.5 * torch.sum(
            logtwopi + self.logvar + torch.pow(sample - self.mean, 2) / self.var,
            dim=dims,
        )

    def mode(self) -> torch.Tensor:
        return self.mean