zhangtianhao
3 years ago
parent
899236b328
commit
fe2775150d
@ -0,0 +1,91 @@
|
||||
############################################
|
||||
# Network Architecture #
|
||||
############################################
|
||||
cmvn_file:
|
||||
cmvn_file_type: "json"
|
||||
# encoder related
|
||||
encoder: conformer
|
||||
encoder_conf:
|
||||
output_size: 256 # dimension of attention
|
||||
attention_heads: 4
|
||||
linear_units: 2048 # the number of units of position-wise feed forward
|
||||
num_blocks: 12 # the number of encoder blocks
|
||||
dropout_rate: 0.1
|
||||
positional_dropout_rate: 0.1
|
||||
attention_dropout_rate: 0.0
|
||||
input_layer: conv2d # encoder input type, you can chose conv2d, conv2d6 and conv2d8
|
||||
normalize_before: True
|
||||
cnn_module_kernel: 15
|
||||
use_cnn_module: True
|
||||
activation_type: 'swish'
|
||||
pos_enc_layer_type: 'rel_pos'
|
||||
selfattention_layer_type: 'rel_selfattn'
|
||||
|
||||
# decoder related
|
||||
decoder: transformer
|
||||
decoder_conf:
|
||||
attention_heads: 4
|
||||
linear_units: 2048
|
||||
num_blocks: 6
|
||||
dropout_rate: 0.1
|
||||
positional_dropout_rate: 0.1
|
||||
self_attention_dropout_rate: 0.0
|
||||
src_attention_dropout_rate: 0.0
|
||||
|
||||
# hybrid CTC/attention
|
||||
model_conf:
|
||||
ctc_weight: 0.3
|
||||
lsm_weight: 0.1 # label smoothing option
|
||||
length_normalized_loss: false
|
||||
init_type: 'kaiming_uniform' # !Warning: need to convergence
|
||||
|
||||
###########################################
|
||||
# Data #
|
||||
###########################################
|
||||
train_manifest: data/manifest.train
|
||||
dev_manifest: data/manifest.dev
|
||||
test_manifest: data/manifest.test
|
||||
|
||||
###########################################
|
||||
# Dataloader #
|
||||
###########################################
|
||||
vocab_filepath: data/lang_char/vocab.txt
|
||||
spm_model_prefix: ''
|
||||
unit_type: 'char'
|
||||
preprocess_config: conf/preprocess.yaml
|
||||
feat_dim: 80
|
||||
stride_ms: 10.0
|
||||
window_ms: 25.0
|
||||
sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs
|
||||
batch_size: 32
|
||||
maxlen_in: 512 # if input length > maxlen-in, batchsize is automatically reduced
|
||||
maxlen_out: 150 # if output length > maxlen-out, batchsize is automatically reduced
|
||||
minibatches: 0 # for debug
|
||||
batch_count: auto
|
||||
batch_bins: 0
|
||||
batch_frames_in: 0
|
||||
batch_frames_out: 0
|
||||
batch_frames_inout: 0
|
||||
num_workers: 2
|
||||
subsampling_factor: 1
|
||||
num_encs: 1
|
||||
|
||||
###########################################
|
||||
# Training #
|
||||
###########################################
|
||||
n_epoch: 150
|
||||
accum_grad: 8
|
||||
global_grad_clip: 5.0
|
||||
dist_sampler: False
|
||||
optim: adam
|
||||
optim_conf:
|
||||
lr: 0.002
|
||||
weight_decay: 1.0e-6
|
||||
scheduler: warmuplr
|
||||
scheduler_conf:
|
||||
warmup_steps: 25000
|
||||
lr_decay: 1.0
|
||||
log_interval: 100
|
||||
checkpoint:
|
||||
kbest_n: 50
|
||||
latest_n: 5
|
||||
@ -0,0 +1,4 @@
|
||||
process:
|
||||
# use raw audio
|
||||
- type: wav_process
|
||||
dither: 0.0
|
||||
@ -0,0 +1,11 @@
|
||||
beam_size: 10
|
||||
decode_batch_size: 128
|
||||
error_rate_type: cer
|
||||
decoding_method: attention # 'attention', 'ctc_greedy_search', 'ctc_prefix_beam_search', 'attention_rescoring'
|
||||
ctc_weight: 0.5 # ctc weight for attention rescoring decode mode.
|
||||
decoding_chunk_size: 16 # decoding chunk size. Defaults to -1.
|
||||
# <0: for decoding, use full chunk.
|
||||
# >0: for decoding, use fixed chunk size as set.
|
||||
# 0: used for training, it's prohibited here.
|
||||
num_decoding_left_chunks: -1 # number of left chunks for decoding. Defaults to -1.
|
||||
simulate_streaming: True # simulate streaming inference. Defaults to False.
|
||||
@ -0,0 +1,11 @@
|
||||
beam_size: 10
|
||||
decode_batch_size: 128
|
||||
error_rate_type: cer
|
||||
decoding_method: attention # 'attention', 'ctc_greedy_search', 'ctc_prefix_beam_search', 'attention_rescoring'
|
||||
ctc_weight: 0.5 # ctc weight for attention rescoring decode mode.
|
||||
decoding_chunk_size: -1 # decoding chunk size. Defaults to -1.
|
||||
# <0: for decoding, use full chunk.
|
||||
# >0: for decoding, use fixed chunk size as set.
|
||||
# 0: used for training, it's prohibited here.
|
||||
num_decoding_left_chunks: -1 # number of left chunks for decoding. Defaults to -1.
|
||||
simulate_streaming: False # simulate streaming inference. Defaults to False.
|
||||
@ -0,0 +1,137 @@
|
||||
############################################
|
||||
# Network Architecture #
|
||||
############################################
|
||||
freeze_wav2vec2: False
|
||||
normalize_wav: True
|
||||
output_norm: True
|
||||
dnn_blocks: 2
|
||||
dnn_neurons: 1024
|
||||
blank_id: 0
|
||||
ctc_dropout_rate: 0.0
|
||||
wav2vec2_params_path: exp/wav2vec2/chinese-wav2vec2-large.pdparams
|
||||
|
||||
############################################
|
||||
# Wav2Vec2.0 #
|
||||
############################################
|
||||
vocab_size: 32
|
||||
hidden_size: 1024
|
||||
num_hidden_layers: 24
|
||||
num_attention_heads: 16
|
||||
intermediate_size: 4096
|
||||
hidden_act: gelu
|
||||
hidden_dropout: 0.1
|
||||
activation_dropout: 0.0
|
||||
attention_dropout: 0.1
|
||||
feat_proj_dropout: 0.1
|
||||
feat_quantizer_dropout: 0.0
|
||||
final_dropout: 0.0
|
||||
layerdrop: 0.1
|
||||
initializer_range: 0.02
|
||||
layer_norm_eps: 1e-5
|
||||
feat_extract_norm: layer
|
||||
feat_extract_activation: gelu
|
||||
conv_dim: [512, 512, 512, 512, 512, 512, 512]
|
||||
conv_stride: [5, 2, 2, 2, 2, 2, 2]
|
||||
conv_kernel: [10, 3, 3, 3, 3, 2, 2]
|
||||
conv_bias: True
|
||||
num_conv_pos_embeddings: 128
|
||||
num_conv_pos_embedding_groups: 16
|
||||
do_stable_layer_norm: True
|
||||
apply_spec_augment: False
|
||||
mask_channel_length: 10
|
||||
mask_channel_min_space: 1
|
||||
mask_channel_other: 0.0
|
||||
mask_channel_prob: 0.0
|
||||
mask_channel_selection: static
|
||||
mask_feature_length: 10
|
||||
mask_feature_min_masks: 0
|
||||
mask_feature_prob: 0.0
|
||||
mask_time_length: 10
|
||||
mask_time_min_masks: 2
|
||||
mask_time_min_space: 1
|
||||
mask_time_other: 0.0
|
||||
mask_time_prob: 0.075
|
||||
mask_time_selection: static
|
||||
num_codevectors_per_group: 320
|
||||
num_codevector_groups: 2
|
||||
contrastive_logits_temperature: 0.1
|
||||
num_negatives: 100
|
||||
codevector_dim: 256
|
||||
proj_codevector_dim: 256
|
||||
diversity_loss_weight: 0.1
|
||||
use_weighted_layer_sum: False
|
||||
pad_token_id: 0
|
||||
bos_token_id: 1
|
||||
eos_token_id: 2
|
||||
add_adapter: False
|
||||
adapter_kernel_size: 3
|
||||
adapter_stride: 2
|
||||
num_adapter_layers: 3
|
||||
output_hidden_size: None
|
||||
|
||||
###########################################
|
||||
# Data #
|
||||
###########################################
|
||||
train_manifest: data/manifest.train
|
||||
dev_manifest: data/manifest.dev
|
||||
test_manifest: data/manifest.test
|
||||
|
||||
|
||||
###########################################
|
||||
# Dataloader #
|
||||
###########################################
|
||||
vocab_filepath: data/lang_char/vocab.txt
|
||||
unit_type: 'char'
|
||||
mean_std_filepath:
|
||||
preprocess_config: conf/preprocess.yaml
|
||||
sortagrad: -1 # Feed samples from shortest to longest ; -1: enabled for all epochs 0: disabled other: enabled for 'other' epochs
|
||||
batch_size: 8 # Different batch_size may cause large differences in results
|
||||
maxlen_in: 51200000000 # if input length > maxlen-in batchsize is automatically reduced
|
||||
maxlen_out: 1500000 # if output length > maxlen-out batchsize is automatically reduced
|
||||
minibatches: 0 # for debug
|
||||
batch_count: auto
|
||||
batch_bins: 0
|
||||
batch_frames_in: 0
|
||||
batch_frames_out: 0
|
||||
batch_frames_inout: 0
|
||||
num_workers: 0
|
||||
subsampling_factor: 1
|
||||
num_encs: 1
|
||||
dist_sampler: True
|
||||
shortest_first: True
|
||||
return_lens_rate: True
|
||||
|
||||
|
||||
###########################################
|
||||
# Training #
|
||||
###########################################
|
||||
n_epoch: 80
|
||||
accum_grad: 1
|
||||
global_grad_clip: 3.0
|
||||
model_optim: adadelta
|
||||
model_optim_conf:
|
||||
lr: 0.95
|
||||
epsilon: 1.0e-8
|
||||
rho: 0.95
|
||||
wav2vec2_optim: adam
|
||||
wav2vec2_optim_conf:
|
||||
lr: 0.0001
|
||||
epsilon: 1.0e-8
|
||||
|
||||
model_scheduler: newbobscheduler
|
||||
model_scheduler_conf:
|
||||
improvement_threshold: 0.0025
|
||||
annealing_factor: 0.8
|
||||
patient: 0
|
||||
wav2vec2_scheduler: newbobscheduler
|
||||
wav2vec2_scheduler_conf:
|
||||
improvement_threshold: 0.0025
|
||||
annealing_factor: 0.9
|
||||
patient: 0
|
||||
log_interval: 1
|
||||
checkpoint:
|
||||
kbest_n: 50
|
||||
latest_n: 5
|
||||
augment: True
|
||||
|
||||
|
||||
@ -0,0 +1,95 @@
|
||||
#!/bin/bash
|
||||
|
||||
stage=-1
|
||||
stop_stage=100
|
||||
dict_dir=data/lang_char
|
||||
|
||||
. ${MAIN_ROOT}/utils/parse_options.sh || exit -1;
|
||||
|
||||
mkdir -p data
|
||||
mkdir -p ${dict_dir}
|
||||
TARGET_DIR=${MAIN_ROOT}/dataset
|
||||
mkdir -p ${TARGET_DIR}
|
||||
|
||||
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
|
||||
# download data, generate manifests
|
||||
python3 ${TARGET_DIR}/aishell/aishell.py \
|
||||
--manifest_prefix="data/manifest" \
|
||||
--target_dir="${TARGET_DIR}/aishell"
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Prepare Aishell failed. Terminated."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for dataset in train dev test; do
|
||||
mv data/manifest.${dataset} data/manifest.${dataset}.raw
|
||||
done
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
|
||||
# compute mean and stddev for normalizer
|
||||
num_workers=$(nproc)
|
||||
python3 ${MAIN_ROOT}/utils/compute_mean_std.py \
|
||||
--manifest_path="data/manifest.train.raw" \
|
||||
--spectrum_type="fbank" \
|
||||
--feat_dim=80 \
|
||||
--delta_delta=false \
|
||||
--stride_ms=10 \
|
||||
--window_ms=25 \
|
||||
--sample_rate=16000 \
|
||||
--use_dB_normalization=False \
|
||||
--num_samples=-1 \
|
||||
--num_workers=${num_workers} \
|
||||
--output_path="data/mean_std.json"
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Compute mean and stddev failed. Terminated."
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
||||
# download data, generate manifests
|
||||
# build vocabulary
|
||||
python3 ${MAIN_ROOT}/utils/build_vocab.py \
|
||||
--unit_type="char" \
|
||||
--count_threshold=0 \
|
||||
--vocab_path="${dict_dir}/vocab.txt" \
|
||||
--manifest_paths "data/manifest.train.raw"
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Build vocabulary failed. Terminated."
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
|
||||
# format manifest with tokenids, vocab size
|
||||
for dataset in train dev test; do
|
||||
{
|
||||
python3 ${MAIN_ROOT}/utils/format_data.py \
|
||||
--cmvn_path "data/mean_std.json" \
|
||||
--unit_type "char" \
|
||||
--vocab_path="${dict_dir}/vocab.txt" \
|
||||
--manifest_path="data/manifest.${dataset}.raw" \
|
||||
--output_path="data/manifest.${dataset}"
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Formt mnaifest failed. Terminated."
|
||||
exit 1
|
||||
fi
|
||||
} &
|
||||
done
|
||||
wait
|
||||
fi
|
||||
echo "Aishell data preparation done."
|
||||
|
||||
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
|
||||
mkdir -p exp/wav2vec2
|
||||
echo "Pretrained wav2vec2 model download"
|
||||
wget -P exp/wav2vec2 https://paddlespeech.bj.bcebos.com/wav2vec/chinese-wav2vec2-large.pdparams
|
||||
fi
|
||||
|
||||
exit 0
|
||||
|
||||
@ -0,0 +1,84 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
echo "using $ngpu gpus..."
|
||||
|
||||
expdir=exp
|
||||
datadir=data
|
||||
|
||||
train_set=train_960
|
||||
recog_set="test-clean test-other dev-clean dev-other"
|
||||
recog_set="test-clean"
|
||||
|
||||
config_path=$1
|
||||
decode_config_path=$2
|
||||
ckpt_prefix=$3
|
||||
|
||||
source ${MAIN_ROOT}/utils/parse_options.sh || exit 1;
|
||||
|
||||
# download language model
|
||||
#bash local/download_lm_en.sh
|
||||
#if [ $? -ne 0 ]; then
|
||||
# exit 1
|
||||
#fi
|
||||
|
||||
python3 utils/format_rsl.py \
|
||||
--origin_ref data/manifest.test-clean.raw \
|
||||
--trans_ref data/manifest.test-clean.text
|
||||
|
||||
|
||||
for type in ctc_greedy_search; do
|
||||
echo "decoding ${type}"
|
||||
batch_size=16
|
||||
python3 -u ${BIN_DIR}/test.py \
|
||||
--ngpu ${ngpu} \
|
||||
--config ${config_path} \
|
||||
--decode_cfg ${decode_config_path} \
|
||||
--result_file ${ckpt_prefix}.${type}.rsl \
|
||||
--checkpoint_path ${ckpt_prefix} \
|
||||
--opts decode.decoding_method ${type} \
|
||||
--opts decode.decode_batch_size ${batch_size}
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Failed in evaluation!"
|
||||
exit 1
|
||||
fi
|
||||
python3 utils/format_rsl.py \
|
||||
--origin_hyp ${ckpt_prefix}.${type}.rsl \
|
||||
--trans_hyp ${ckpt_prefix}.${type}.rsl.text
|
||||
|
||||
python3 utils/compute-wer.py --char=1 --v=1 \
|
||||
data/manifest.test-clean.text ${ckpt_prefix}.${type}.rsl.text > ${ckpt_prefix}.${type}.error
|
||||
echo "decoding ${type} done."
|
||||
done
|
||||
|
||||
for type in ctc_prefix_beam_search; do
|
||||
echo "decoding ${type}"
|
||||
batch_size=1
|
||||
python3 -u ${BIN_DIR}/test.py \
|
||||
--ngpu ${ngpu} \
|
||||
--config ${config_path} \
|
||||
--decode_cfg ${decode_config_path} \
|
||||
--result_file ${ckpt_prefix}.${type}.rsl \
|
||||
--checkpoint_path ${ckpt_prefix} \
|
||||
--opts decode.decoding_method ${type} \
|
||||
--opts decode.decode_batch_size ${batch_size}
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Failed in evaluation!"
|
||||
exit 1
|
||||
fi
|
||||
python3 utils/format_rsl.py \
|
||||
--origin_hyp ${ckpt_prefix}.${type}.rsl \
|
||||
--trans_hyp ${ckpt_prefix}.${type}.rsl.text
|
||||
|
||||
python3 utils/compute-wer.py --char=1 --v=1 \
|
||||
data/manifest.test-clean.text ${ckpt_prefix}.${type}.rsl.text > ${ckpt_prefix}.${type}.error
|
||||
echo "decoding ${type} done."
|
||||
done
|
||||
|
||||
echo "Finished"
|
||||
|
||||
exit 0
|
||||
@ -0,0 +1,58 @@
|
||||
#!/bin/bash
|
||||
|
||||
if [ $# != 4 ];then
|
||||
echo "usage: ${0} config_path decode_config_path ckpt_path_prefix audio_file"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
echo "using $ngpu gpus..."
|
||||
|
||||
config_path=$1
|
||||
decode_config_path=$2
|
||||
ckpt_prefix=$3
|
||||
audio_file=$4
|
||||
|
||||
mkdir -p data
|
||||
wget -nc https://paddlespeech.bj.bcebos.com/datasets/single_wav/en/demo_002_en.wav -P data/
|
||||
if [ $? -ne 0 ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ ! -f ${audio_file} ]; then
|
||||
echo "Plase input the right audio_file path"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
chunk_mode=false
|
||||
if [[ ${config_path} =~ ^.*chunk_.*yaml$ ]];then
|
||||
chunk_mode=true
|
||||
fi
|
||||
|
||||
# download language model
|
||||
#bash local/download_lm_ch.sh
|
||||
#if [ $? -ne 0 ]; then
|
||||
# exit 1
|
||||
#fi
|
||||
|
||||
for type in ctc_greedy_search; do
|
||||
echo "decoding ${type}"
|
||||
batch_size=1
|
||||
output_dir=${ckpt_prefix}
|
||||
mkdir -p ${output_dir}
|
||||
python3 -u ${BIN_DIR}/test_wav.py \
|
||||
--ngpu ${ngpu} \
|
||||
--config ${config_path} \
|
||||
--decode_cfg ${decode_config_path} \
|
||||
--result_file ${output_dir}/${type}.rsl \
|
||||
--checkpoint_path ${ckpt_prefix} \
|
||||
--opts decode.decoding_method ${type} \
|
||||
--opts decode.decode_batch_size ${batch_size} \
|
||||
--audio_file ${audio_file}
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Failed in evaluation!"
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
exit 0
|
||||
@ -0,0 +1,56 @@
|
||||
#!/bin/bash
|
||||
|
||||
if [ $# -lt 2 ] && [ $# -gt 3 ];then
|
||||
echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
|
||||
echo "using $ngpu gpus..."
|
||||
|
||||
config_path=$1
|
||||
ckpt_name=$2
|
||||
ips=$3
|
||||
|
||||
if [ ! $ips ];then
|
||||
ips_config=
|
||||
else
|
||||
ips_config="--ips="${ips}
|
||||
fi
|
||||
|
||||
mkdir -p exp
|
||||
|
||||
# seed may break model convergence
|
||||
seed=1998
|
||||
if [ ${seed} != 0 ]; then
|
||||
export FLAGS_cudnn_deterministic=True
|
||||
fi
|
||||
|
||||
# export FLAGS_cudnn_exhaustive_search=true
|
||||
# export FLAGS_conv_workspace_size_limit=4000
|
||||
# export FLAGS_allocator_strategy=naive_best_fit
|
||||
|
||||
if [ ${ngpu} == 0 ]; then
|
||||
python3 -u ${BIN_DIR}/train.py \
|
||||
--ngpu ${ngpu} \
|
||||
--config ${config_path} \
|
||||
--output exp/${ckpt_name} \
|
||||
--seed ${seed}
|
||||
else
|
||||
python3 -m paddle.distributed.launch --log_dir=aa --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
|
||||
--ngpu ${ngpu} \
|
||||
--config ${config_path} \
|
||||
--output exp/${ckpt_name} \
|
||||
--seed ${seed}
|
||||
fi
|
||||
|
||||
if [ ${seed} != 0 ]; then
|
||||
unset FLAGS_cudnn_deterministic
|
||||
fi
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Failed in training!"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
exit 0
|
||||
@ -0,0 +1,15 @@
|
||||
export MAIN_ROOT=`realpath ${PWD}/../../../`
|
||||
|
||||
export PATH=${MAIN_ROOT}:${MAIN_ROOT}/tools/sctk/bin:${PWD}/utils:${PATH}
|
||||
export LC_ALL=C
|
||||
|
||||
export PYTHONDONTWRITEBYTECODE=1
|
||||
# Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
|
||||
export PYTHONIOENCODING=UTF-8
|
||||
export PYTHONPATH=${MAIN_ROOT}:${PYTHONPATH}
|
||||
|
||||
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib/
|
||||
|
||||
|
||||
MODEL=wav2vec2
|
||||
export BIN_DIR=${MAIN_ROOT}/paddlespeech/s2t/exps/${MODEL}/bin
|
||||
@ -0,0 +1,46 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
. ./path.sh || exit 1;
|
||||
. ./cmd.sh || exit 1;
|
||||
|
||||
gpus=6
|
||||
stage=1
|
||||
stop_stage=1
|
||||
conf_path=conf/wav2vec2ASR.yaml
|
||||
ips= #xx.xx.xx.xx,xx.xx.xx.xx
|
||||
decode_conf_path=conf/tuning/decode.yaml
|
||||
avg_num=1
|
||||
|
||||
. ${MAIN_ROOT}/utils/parse_options.sh || exit 1;
|
||||
|
||||
audio_file=data/demo_002_en.wav
|
||||
|
||||
avg_ckpt=avg_${avg_num}
|
||||
ckpt=$(basename ${conf_path} | awk -F'.' '{print $1}')
|
||||
echo "checkpoint name ${ckpt}"
|
||||
|
||||
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
|
||||
# prepare data
|
||||
bash ./local/data.sh || exit -1
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
|
||||
# train model, all `ckpt` under `exp` dir
|
||||
CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
|
||||
# avg n best model
|
||||
avg.sh best exp/${ckpt}/checkpoints ${avg_num}
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
|
||||
# greedy search decoder
|
||||
CUDA_VISIBLE_DEVICES=${gpus} ./local/test.sh ${conf_path} ${decode_conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
|
||||
fi
|
||||
|
||||
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
|
||||
# test a single .wav file
|
||||
CUDA_VISIBLE_DEVICES=${gpus} ./local/test_wav.sh ${conf_path} ${decode_conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} ${audio_file} || exit -1
|
||||
fi
|
||||
@ -0,0 +1 @@
|
||||
../../../utils
|
||||
Loading…
Reference in new issue