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/decoders/swig/ctc_greedy_decoder.cpp

60 lines
2.0 KiB

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
// 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.
#include "ctc_greedy_decoder.h"
#include "decoder_utils.h"
std::string ctc_greedy_decoder(
const std::vector<std::vector<double>> &probs_seq,
const std::vector<std::string> &vocabulary) {
// dimension check
size_t num_time_steps = probs_seq.size();
for (size_t i = 0; i < num_time_steps; ++i) {
VALID_CHECK_EQ(probs_seq[i].size(),
vocabulary.size() + 1,
"The shape of probs_seq does not match with "
"the shape of the vocabulary");
}
size_t blank_id = vocabulary.size();
std::vector<size_t> max_idx_vec(num_time_steps, 0);
std::vector<size_t> idx_vec;
for (size_t i = 0; i < num_time_steps; ++i) {
double max_prob = 0.0;
size_t max_idx = 0;
const std::vector<double> &probs_step = probs_seq[i];
for (size_t j = 0; j < probs_step.size(); ++j) {
if (max_prob < probs_step[j]) {
max_idx = j;
max_prob = probs_step[j];
}
}
// id with maximum probability in current time step
max_idx_vec[i] = max_idx;
// deduplicate
if ((i == 0) || ((i > 0) && max_idx_vec[i] != max_idx_vec[i - 1])) {
idx_vec.push_back(max_idx_vec[i]);
}
}
std::string best_path_result;
for (size_t i = 0; i < idx_vec.size(); ++i) {
if (idx_vec[i] != blank_id) {
best_path_result += vocabulary[idx_vec[i]];
}
}
return best_path_result;
}