You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
PaddleSpeech/deepspeech/frontend/augmentor/volume_perturb.py

50 lines
1.7 KiB

4 years ago
# Copyright (c) 2021 PaddlePaddle Authors. 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.
"""Contains the volume perturb augmentation model."""
Support paddle 2.x (#538) * 2.x model * model test pass * fix data * fix soundfile with flac support * one thread dataloader test pass * export feasture size add trainer and utils add setup model and dataloader update travis using Bionic dist * add venv; test under venv * fix unittest; train and valid * add train and config * add config and train script * fix ctc cuda memcopy error * fix imports * fix train valid log * fix dataset batch shuffle shift start from 1 fix rank_zero_only decreator error close tensorboard when train over add decoding config and code * test process can run * test with decoding * test and infer with decoding * fix infer * fix ctc loss lr schedule sortagrad logger * aishell egs * refactor train add aishell egs * fix dataset batch shuffle and add batch sampler log print model parameter * fix model and ctc * sequence_mask make all inputs zeros, which cause grad be zero, this is a bug of LessThanOp add grad clip by global norm add model train test notebook * ctc loss remove run prefix using ord value as text id * using unk when training compute_loss need text ids ord id using in test mode, which compute wer/cer * fix tester * add lr_deacy refactor code * fix tools * fix ci add tune fix gru model bugs add dataset and model test * fix decoding * refactor repo fix decoding * fix musan and rir dataset * refactor io, loss, conv, rnn, gradclip, model, utils * fix ci and import * refactor model add export jit model * add deploy bin and test it * rm uselss egs * add layer tools * refactor socket server new model from pretrain * remve useless * fix instability loss and grad nan or inf for librispeech training * fix sampler * fix libri train.sh * fix doc * add license on cpp * fix doc * fix libri script * fix install * clip 5 wer 7.39, clip 400 wer 7.54, 1.8 clip 400 baseline 7.49
4 years ago
from deepspeech.frontend.augmentor.base import AugmentorBase
class VolumePerturbAugmentor(AugmentorBase):
"""Augmentation model for adding random volume perturbation.
This is used for multi-loudness training of PCEN. See
https://arxiv.org/pdf/1607.05666v1.pdf
for more details.
:param rng: Random generator object.
:type rng: random.Random
:param min_gain_dBFS: Minimal gain in dBFS.
:type min_gain_dBFS: float
:param max_gain_dBFS: Maximal gain in dBFS.
:type max_gain_dBFS: float
"""
def __init__(self, rng, min_gain_dBFS, max_gain_dBFS):
self._min_gain_dBFS = min_gain_dBFS
self._max_gain_dBFS = max_gain_dBFS
self._rng = rng
def transform_audio(self, audio_segment):
"""Change audio loadness.
Note that this is an in-place transformation.
:param audio_segment: Audio segment to add effects to.
:type audio_segment: AudioSegmenet|SpeechSegment
"""
gain = self._rng.uniform(self._min_gain_dBFS, self._max_gain_dBFS)
audio_segment.gain_db(gain)