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/examples/ted_en_zh/st1
TianYuan 69138a2c85
update readme, test=doc_fix (#1156)
3 years ago
..
conf remove ctc grad norm type in config 3 years ago
local minor updates 3 years ago
.gitignore refactor: rename t1 to st1 3 years ago
README.md update readme, test=doc_fix (#1156) 3 years ago
RESULTS.md rename to result.md 3 years ago
cmd.sh update cmd.sh 3 years ago
path.sh minor updates 3 years ago
run.sh minor updates 3 years ago
steps process scripts and configs 3 years ago
utils process scripts and configs 3 years ago

README.md

Transformer/Conformer ST1 with TED_En_Zh

This example contains code used to train a Transformer or Conformer model with TED_EN_Zh.

To use this example, you need to install Kaldi first.

The main difference between st0 and st1 is that st1 uses kaldi feature.

Overview

All the scripts you need are in run.sh. There are several stages in run.sh, and each stage has its function.

You need to download TED_En_Zh dataset by yourself.

Stage Function
0 Process data. It includes:
(1) Calculate the CMVN of the train dataset
(2) Get the vocabulary file
(3) Get the manifest files of the train, development and test dataset
1 Train the model
2 Get the final model by averaging the top-k models, set k = 1 means to choose the best model
3 Test the final model performance

You can choose to run a range of stages by setting stage and stop_stage .

For example, if you want to execute the code in stage 2 and stage 3, you can run this script:

bash run.sh --stage 2 --stop_stage 3

Or you can set stage equal to stop-stage to only run one stage. For example, if you only want to run stage 0, you can use the script below:

bash run.sh --stage 0 --stop_stage 0

The document below will describe the scripts in run.shin detail.

The Environment Variables

The path.sh contains the environment variables.

. ./path.sh
. ./cmd.sh

This script needs to be run first. And another script is also needed:

source ${MAIN_ROOT}/utils/parse_options.sh

It will support the way of using --variable value in the shell scripts.

The Local Variables

Some local variables are set in run.sh. gpus denotes the GPU number you want to use. If you set gpus=, it means you only use CPU. stage denotes the number of the stage you want to start from in the experiments. stop stage denotes the number of the stage you want to end at in the experiments. conf_path denotes the config path of the model. data_path denotes the path of the dataset. avg_numdenotes the number K of top-K models you want to average to get the final model. ckpt denotes the checkpoint prefix of the model, e.g. "transformer_mtl_noam"

You can set the local variables (except ckpt) when you use run.sh

For example, you can set the gpus and avg_num when you use the command line.:

bash run.sh --gpus 0,1 --avg_num 5

Stage 0: Data Processing

To use this example, you need to process data firstly and you can use stage 0 in run.shto do this. The code is shown below:

 if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
     # prepare data
     bash ./local/data.sh || exit -1
 fi

Stage 0 is for processing the data.

If you only want to process the data. You can run

bash run.sh --stage 0 --stop_stage 0

You can also just run these scripts in your command line.

. ./path.sh
. ./cmd.sh
bash ./local/data.sh

Stage 1: Model Training

If you want to train the model. you can use stage 1 in run.sh. The code is shown below.

if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    # train model, all `ckpt` under `exp` dir
    if [ -n "${ckpt_path}" ]; then
        echo "Finetune from Pretrained Model" ${ckpt_path}
        ./local/download_pretrain.sh || exit -1
    fi 
    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} "${ckpt_path}"
fi

If you want to train the model, you can use the script below to execute stage 0 and stage 1:

bash run.sh --stage 0 --stop_stage 1

or you can run these scripts in the command line (only use CPU).

. ./path.sh
. ./cmd.sh
bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer_mtl_noam.yaml transformer_mtl_noam ""

Stage 2: Top-k Models Averaging

After training the model, we need to get the final model for testing and inference. In every epoch, the model checkpoint is saved, so we can choose the best model from them based on the validation loss or we can sort them and average the parameters of the top-k models to get the final model. We can use stage 2 to do this, and the code is shown below:

if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
    # avg n best model
    avg.sh best exp/${ckpt}/checkpoints ${avg_num}
fi

The avg.shis in the ../../../utils/which is define in the path.sh. If you want to get the final model, you can use the script below to execute stage 0, stage 1, and stage 2:

bash run.sh --stage 0 --stop_stage 2

or you can run these scripts in the command line (only use CPU).

. ./path.sh
. ./cmd.sh
bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer_mtl_noam.yaml transformer_mtl_noam
avg.sh best exp/transformer_mtl_noam/checkpoints 5

Stage 3: Model Testing

The stage 3 is to evaluate the model performance. The code of this stage is shown below:

if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
    # test ckpt avg_n
    CUDA_VISIBLE_DEVICES=0 ./local/test.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
fi

If you want to train a model and test it, you can use the script below to execute stage 0, stage 1, stage 2, and stage 3 :

bash run.sh --stage 0 --stop_stage 3

or you can run these scripts in the command line (only use CPU).

. ./path.sh
. ./cmd.sh
bash ./local/data.sh
CUDA_VISIBLE_DEVICES= ./local/train.sh conf/transformer_mtl_noam.yaml transformer_mtl_noam
avg.sh latest exp/transformer_mtl_noam/checkpoints 5
CUDA_VISIBLE_DEVICES= ./local/test.sh conf/transformer_mtl_noam.yaml exp/transformer_mtl_noam/checkpoints/avg_5

The performance of the released models are shown below:

Transformer

Model Params Config Val loss Char-BLEU
FAT + Transformer+ASR MTL 50.26M conf/transformer_mtl_noam.yaml 62.86 19.45
FAT + Transformer+ASR MTL with word reward 50.26M conf/transformer_mtl_noam.yaml 62.86 20.80