wehub-resource-sync
ba4be087d5
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
CICD NeMo / cicd-test-container-build (push) Has been cancelled
CICD NeMo / cicd-import-tests (push) Has been cancelled
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Has been cancelled
CICD NeMo / cicd-main-unit-tests (push) Has been cancelled
CICD NeMo / cicd-main-speech (push) Has been cancelled
CICD NeMo / Nemo_CICD_Test (push) Has been cancelled
CICD NeMo / Coverage (e2e) (push) Has been cancelled
CICD NeMo / Coverage (unit-test) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
CICD NeMo / cicd-wait-in-queue (push) Has been cancelled
36 lines
1.3 KiB
Python
36 lines
1.3 KiB
Python
# 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
|