fix s0 scripts

examples/aishell/s0/conf/deepspeech2.yaml

@@ -22,18 +22,21 @@ data:
   sortagrad: True
   shuffle_method: batch_shuffle
   num_workers: 0
+
 model:
   num_conv_layers: 2
   num_rnn_layers: 3
   rnn_layer_size: 1024
   use_gru: True 
   share_rnn_weights: False
+
 training:
   n_epoch: 50
   lr: 2e-3
   lr_decay: 0.83
   weight_decay: 1e-06
   global_grad_clip: 5.0
+  
 decoding:
   batch_size: 128
   error_rate_type: cer 

examples/aishell/s0/local/infer.sh

-#! /usr/bin/env bash
-
-if [[ $# != 1 ]]; then
-    echo "usage: $0 ckpt-path"
-    exit -1
-fi
-
-# download language model
-bash local/download_lm_ch.sh
-if [ $? -ne 0 ]; then
-    exit 1
-fi
-
-python3 -u ${BIN_DIR}/infer.py \
---device 'gpu' \
---nproc 1 \
---config conf/deepspeech2.yaml \
---checkpoint_path ${1} 
-
-
-if [ $? -ne 0 ]; then
-    echo "Failed in inference!"
-    exit 1
-fi
-
-
-exit 0

examples/aishell/s0/local/test.sh

 #! /usr/bin/env bash
 
+if [[ $# != 1 ]]; then
+    echo "usage: $0 ckpt-path"
+    exit -1
+fi
+
 # download language model
 bash local/download_lm_ch.sh
 if [ $? -ne 0 ]; then
     exit 1
 fi
 
-python3 -u ${BIN_DIR}/test.py \
+python3 -u ${BIN_DIR}/infer.py \
 --device 'gpu' \
 --nproc 1 \
 --config conf/deepspeech2.yaml \
---output ckpt
+--checkpoint_path ${1} 
+
 
 if [ $? -ne 0 ]; then
-    echo "Failed in evaluation!"
+    echo "Failed in inference!"
     exit 1
 fi
 

examples/aishell/s1/conf/conformer.yaml

@@ -24,7 +24,7 @@ data:
   n_fft: None
   stride_ms: 10.0
   window_ms: 25.0
-  use_dB_normalization: True
+  use_dB_normalization: False 
   target_dB: -20
   random_seed: 0
   keep_transcription_text: False
@@ -74,7 +74,7 @@ model:
 
 
 training:
-  n_epoch: 240
+  n_epoch: 300
   accum_grad: 2
   global_grad_clip: 5.0
   optim: adam

examples/librispeech/s0/local/download_model.sh

-#! /usr/bin/env bash
-
-. ${MAIN_ROOT}/utils/utility.sh
-
-DIR=data/pretrain
-mkdir -p ${DIR}
-
-URL='https://deepspeech.bj.bcebos.com/eng_models/librispeech_model_fluid.tar.gz'
-MD5=fafb11fe57c3ecd107147056453f5348
-TARGET=${DIR}/librispeech_model_fluid.tar.gz
-
-
-echo "Download LibriSpeech model ..."
-download $URL $MD5 $TARGET
-if [ $? -ne 0 ]; then
-    echo "Fail to download LibriSpeech model!"
-    exit 1
-fi
-tar -zxvf $TARGET -C ${DIR}
-
-exit 0

examples/librispeech/s0/local/export.sh

 #! /usr/bin/env bash
 
-if [ $# != 2 ];then
-    echo "usage: export ckpt_path jit_model_path"
+if [ $# != 3 ];then
+    echo "usage: $0 config_path ckpt_prefix jit_model_path"
     exit -1
 fi
 
+ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+echo "using $ngpu gpus..."
+
+config_path=$1
+ckpt_path_prefix=$2
+jit_model_export_path=$3
+
+device=gpu
+if [ ngpu == 0 ];then
+    device=cpu
+fi
+
 python3 -u ${BIN_DIR}/export.py \
---config conf/deepspeech2.yaml \
---checkpoint_path ${1} \
---export_path ${2} 
+--device ${device} \
+--nproc ${ngpu} \
+--config ${config_path} \
+--checkpoint_path ${ckpt_path_prefix} \
+--export_path ${jit_model_export_path}
 
 
 if [ $? -ne 0 ]; then
-    echo "Failed in evaluation!"
+    echo "Failed in export!"
     exit 1
 fi
 

examples/librispeech/s0/local/infer.sh

-#! /usr/bin/env bash
-
-if [[ $# != 1 ]];then
-    echo "usage: $0 ckpt-path"
-    exit -1
-fi
-
-# download language model
-bash local/download_lm_en.sh
-if [ $? -ne 0 ]; then
-    exit 1
-fi
-
-python3 -u ${BIN_DIR}/infer.py \
---device 'gpu' \
---nproc 1 \
---config conf/deepspeech2.yaml \
---checkpoint_path ${1} 
-
-if [ $? -ne 0 ]; then
-    echo "Failed in inference!"
-    exit 1
-fi
-
-exit 0

examples/librispeech/s0/local/test.sh

 #! /usr/bin/env bash
 
+if [ $# != 2 ];then
+    echo "usage: ${0} config_path ckpt_path_prefix"
+    exit -1
+fi
+
+ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+echo "using $ngpu gpus..."
+
+device=gpu
+if [ ngpu == 0 ];then
+    device=cpu
+fi
+config_path=$1
+ckpt_prefix=$2
+
 # download language model
 bash local/download_lm_en.sh
 if [ $? -ne 0 ]; then
-    exit 1
+   exit 1
 fi
 
 python3 -u ${BIN_DIR}/test.py \
---device 'gpu' \
+--device ${device} \
 --nproc 1 \
---config conf/deepspeech2.yaml \
---output ckpt
-
+--config ${config_path} \
+--result_file ${ckpt_prefix}.rsl \
+--checkpoint_path ${ckpt_prefix}
 
 if [ $? -ne 0 ]; then
     echo "Failed in evaluation!"

examples/librispeech/s0/local/train.sh

 #! /usr/bin/env bash
 
-#export FLAGS_sync_nccl_allreduce=0
-
-# https://github.com/PaddlePaddle/Paddle/pull/28484
-#export NCCL_SHM_DISABLE=1
+if [ $# != 2 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+    exit -1
+fi
 
-ngpu=$(echo ${CUDA_VISIBLE_DEVICES} | python -c 'import sys; a = sys.stdin.read(); print(len(a.split(",")));')
+ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
 echo "using $ngpu gpus..."
 
+config_path=$1
+ckpt_name=$2
+
+device=gpu
+if [ ngpu == 0 ];then
+    device=cpu
+fi
+echo "using ${device}..."
+
+mkdir -p exp
+
 python3 -u ${BIN_DIR}/train.py \
---device 'gpu' \
+--device ${device} \
 --nproc ${ngpu} \
---config conf/deepspeech2.yaml \
---output ckpt-${1}
+--config ${config_path} \
+--output exp/${ckpt_name}
 
 if [ $? -ne 0 ]; then
     echo "Failed in training!"
     exit 1
 fi
 
-
 exit 0

examples/librispeech/s0/run.sh

 #!/bin/bash
 set -e
-
 source path.sh
 
-# prepare data
-bash ./local/data.sh
+stage=0
+stop_stage=100
+conf_path=conf/deepspeech2.yaml
+ckpt=$(basename ${conf_path} | awk -F'.' '{print $1}')
+avg_num=1
+avg_ckpt=avg_${avg_num}
+
+source ${MAIN_ROOT}/utils/parse_options.sh || exit 1;
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    # prepare data
+    bash ./local/data.sh || exit -1
+fi
 
-# train model
-CUDA_VISIBLE_DEVICES=0,1,2,3 bash ./local/train.sh
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    # train model, all `ckpt` under `exp` dir
+    CUDA_VISIBLE_DEVICES=4,5,6,7 ./local/train.sh ${conf_path}  ${ckpt}
+fi
 
-# test model
-CUDA_VISIBLE_DEVICES=0  bash ./local/test.sh
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    # avg n best model
+    ./local/avg.sh exp/${ckpt}/checkpoints ${avg_num}
+fi
 
-# infer model
-CUDA_VISIBLE_DEVICES=0  bash ./local/infer.sh ckpt/checkpoints/step-3284
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    # test ckpt avg_n
+    CUDA_VISIBLE_DEVICES=7 ./local/test.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
+fi
 
-# export model
-bash ./local/export.sh ckpt/checkpoints/step-3284 jit.model
\ No newline at end of file
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    # export ckpt avg_n
+    CUDA_VISIBLE_DEVICES= ./local/export.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} exp/${ckpt}/checkpoints/${avg_ckpt}.jit
+fi
\ No newline at end of file

examples/tiny/s0/local/export.sh

 #! /usr/bin/env bash
 
-if [ $# != 2 ];then
-    echo "usage: export ckpt_path jit_model_path"
+if [ $# != 3 ];then
+    echo "usage: $0 config_path ckpt_prefix jit_model_path"
     exit -1
 fi
 
+ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+echo "using $ngpu gpus..."
+
+config_path=$1
+ckpt_path_prefix=$2
+jit_model_export_path=$3
+
+device=gpu
+if [ ngpu == 0 ];then
+    device=cpu
+fi
+
 python3 -u ${BIN_DIR}/export.py \
---config conf/deepspeech2.yaml \
---checkpoint_path ${1} \
---export_path ${2} 
+--device ${device} \
+--nproc ${ngpu} \
+--config ${config_path} \
+--checkpoint_path ${ckpt_path_prefix} \
+--export_path ${jit_model_export_path}
 
 
 if [ $? -ne 0 ]; then
-    echo "Failed in evaluation!"
+    echo "Failed in export!"
     exit 1
 fi
 

examples/tiny/s0/local/infer.sh

-#! /usr/bin/env bash
-
-if [[ $# != 1 ]];then
-    echo "usage: $0 ckpt-path"
-    exit -1
-fi
-
-# download language model
-bash local/download_lm_en.sh
-if [ $? -ne 0 ]; then
-    exit 1
-fi
-
-python3 -u ${BIN_DIR}/infer.py \
---device 'gpu' \
---nproc 1 \
---config conf/deepspeech2.yaml \
---checkpoint_path ${1} 
-
-
-if [ $? -ne 0 ]; then
-    echo "Failed in inference!"
-    exit 1
-fi
-
-exit 0

examples/tiny/s0/local/test.sh

 #! /usr/bin/env bash
 
+if [ $# != 2 ];then
+    echo "usage: ${0} config_path ckpt_path_prefix"
+    exit -1
+fi
+
+ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+echo "using $ngpu gpus..."
+
+device=gpu
+if [ ngpu == 0 ];then
+    device=cpu
+fi
+config_path=$1
+ckpt_prefix=$2
+
 # download language model
 bash local/download_lm_en.sh
 if [ $? -ne 0 ]; then
-    exit 1
+   exit 1
 fi
 
 python3 -u ${BIN_DIR}/test.py \
---device 'gpu' \
+--device ${device} \
 --nproc 1 \
---config conf/deepspeech2.yaml \
---output ckpt
+--config ${config_path} \
+--result_file ${ckpt_prefix}.rsl \
+--checkpoint_path ${ckpt_prefix}
 
 if [ $? -ne 0 ]; then
     echo "Failed in evaluation!"

examples/tiny/s0/local/train.sh

 #! /usr/bin/env bash
 
-export FLAGS_sync_nccl_allreduce=0
+if [ $# != 2 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+    exit -1
+fi
+
+ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+echo "using $ngpu gpus..."
+
+config_path=$1
+ckpt_name=$2
+
+device=gpu
+if [ ngpu == 0 ];then
+    device=cpu
+fi
+
+mkdir -p exp
 
 python3 -u ${BIN_DIR}/train.py \
---device 'gpu' \
---nproc 1 \
---config conf/deepspeech2.yaml \
---output ckpt
+--device ${device} \
+--nproc ${ngpu} \
+--config ${config_path} \
+--output exp/${ckpt_name}
 
 if [ $? -ne 0 ]; then
     echo "Failed in training!"
     exit 1
 fi
 
-
 exit 0

examples/tiny/s0/run.sh

 #!/bin/bash
 set -e
-
 source path.sh
 
-# prepare data
-bash ./local/data.sh
+stage=0
+stop_stage=100
+conf_path=conf/deepspeech2.yaml
+ckpt=$(basename ${conf_path} | awk -F'.' '{print $1}')
+avg_num=1
+avg_ckpt=avg_${avg_num}
+
+source ${MAIN_ROOT}/utils/parse_options.sh || exit 1;
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    # prepare data
+    bash ./local/data.sh || exit -1
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    # train model, all `ckpt` under `exp` dir
+    CUDA_VISIBLE_DEVICES=0 ./local/train.sh ${conf_path}  ${ckpt}
+fi
 
-# train model
-bash ./local/train.sh
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    # avg n best model
+    ./local/avg.sh exp/${ckpt}/checkpoints ${avg_num}
+fi
 
-# test model
-bash ./local/test.sh
+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
 
-# infer model
-bash ./local/infer.sh
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+    # export ckpt avg_n
+    CUDA_VISIBLE_DEVICES= ./local/export.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} exp/${ckpt}/checkpoints/${avg_ckpt}.jit
+fi