tts/utils/audio_utils/align.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

def mel2token_to_dur(mel2token, T_txt=None, max_dur=None):
    is_torch = isinstance(mel2token, torch.Tensor)
    has_batch_dim = True
    if not is_torch:
        mel2token = torch.LongTensor(mel2token)
    if T_txt is None:
        T_txt = mel2token.max()
    if len(mel2token.shape) == 1:
        mel2token = mel2token[None, ...]
        has_batch_dim = False
    B, _ = mel2token.shape
    dur = mel2token.new_zeros(B, T_txt + 1).scatter_add(1, mel2token, torch.ones_like(mel2token))
    dur = dur[:, 1:]
    if max_dur is not None:
        dur = dur.clamp(max=max_dur)
    if not is_torch:
        dur = dur.numpy()
    if not has_batch_dim:
        dur = dur[0]
    return dur