| # Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | |
| # | |
| # 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 | |
| class GreedyCTCDecoder(torch.nn.Module): | |
| def __init__(self, labels, blank=0): | |
| super().__init__() | |
| self.labels = labels | |
| self.blank = blank | |
| def forward(self, emission): | |
| """Given a sequence emission over labels, get the best path | |
| Args: | |
| emission (Tensor): Logit tensors. Shape `[num_seq, num_label]`. | |
| Returns: | |
| List[str]: The resulting transcript | |
| """ | |
| indices = torch.argmax(emission, dim=-1) # [num_seq,] | |
| indices = torch.unique_consecutive(indices, dim=-1) | |
| indices = [i for i in indices if i != self.blank] | |
| joined = "".join([self.labels[i] for i in indices]) | |
| return indices, joined | |