forked from modelscope/FunASR
-
Notifications
You must be signed in to change notification settings - Fork 0
/
run.sh
executable file
·210 lines (188 loc) · 7.27 KB
/
run.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
#!/usr/bin/env bash
. ./path.sh || exit 1;
# machines configuration
CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
gpu_num=8
count=1
gpu_inference=true # Whether to perform gpu decoding, set false for cpu decoding
# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
njob=5
train_cmd=utils/run.pl
infer_cmd=utils/run.pl
# general configuration
feats_dir="../DATA" #feature output dictionary
exp_dir="."
lang=zh
token_type=char
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
stage=0
stop_stage=5
# feature configuration
feats_dim=80
nj=64
# data
raw_data=../raw_data
data_url=www.openslr.org/resources/33
# exp tag
tag="exp1"
. utils/parse_options.sh || exit 1;
# Set bash to 'debug' mode, it will exit on :
# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
set -e
set -u
set -o pipefail
train_set=train
valid_set=dev
test_sets="dev test"
asr_config=conf/train_conformer_bat.yaml
model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
inference_config=conf/decode_bat_conformer.yaml
inference_asr_model=valid.cer_transducer.ave_10best.pb
# you can set gpu num for decoding here
gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
ngpu=$(echo $gpuid_list | awk -F "," '{print NF}')
if ${gpu_inference}; then
inference_nj=$[${ngpu}*${njob}]
_ngpu=1
else
inference_nj=$njob
_ngpu=0
fi
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
echo "stage -1: Data Download"
local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
fi
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo "stage 0: Data preparation"
# Data preparation
local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
for x in train dev test; do
cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
> ${feats_dir}/data/${x}/text
utils/text2token.py -n 1 -s 1 ${feats_dir}/data/${x}/text > ${feats_dir}/data/${x}/text.org
mv ${feats_dir}/data/${x}/text.org ${feats_dir}/data/${x}/text
done
fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
echo "stage 1: Feature and CMVN Generation"
utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
fi
token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
echo "dictionary: ${token_list}"
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
echo "stage 2: Dictionary Preparation"
mkdir -p ${feats_dir}/data/${lang}_token_list/char/
echo "make a dictionary"
echo "<blank>" > ${token_list}
echo "<s>" >> ${token_list}
echo "</s>" >> ${token_list}
utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
| sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
echo "<unk>" >> ${token_list}
fi
# LM Training Stage
world_size=$gpu_num # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
echo "stage 3: LM Training"
fi
# ASR Training Stage
world_size=$gpu_num # run on one machine
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
echo "stage 4: ASR Training"
mkdir -p ${exp_dir}/exp/${model_dir}
mkdir -p ${exp_dir}/exp/${model_dir}/log
INIT_FILE=./ddp_init
if [ -f $INIT_FILE ];then
rm -f $INIT_FILE
fi
init_method=file://$(readlink -f $INIT_FILE)
echo "$0: init method is $init_method"
for ((i = 0; i < $gpu_num; ++i)); do
{
rank=$i
local_rank=$i
gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
train.py \
--task_name asr \
--gpu_id $gpu_id \
--use_preprocessor true \
--token_type char \
--token_list $token_list \
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
--cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
--config $asr_config \
--ngpu $gpu_num \
--num_worker_count $count \
--dist_init_method $init_method \
--dist_world_size $world_size \
--dist_rank $rank \
--local_rank $local_rank 1> ${exp_dir}/exp/${model_dir}/log/train.log.$i 2>&1
} &
done
wait
fi
# Testing Stage
if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
echo "stage 5: Inference"
for dset in ${test_sets}; do
asr_exp=${exp_dir}/exp/${model_dir}
inference_tag="$(basename "${inference_config}" .yaml)"
_dir="${asr_exp}/${inference_tag}/${inference_asr_model}/${dset}"
_logdir="${_dir}/logdir"
if [ -d ${_dir} ]; then
echo "${_dir} is already exists. if you want to decode again, please delete this dir first."
exit 0
fi
mkdir -p "${_logdir}"
_data="${feats_dir}/data/${dset}"
key_file=${_data}/${scp}
num_scp_file="$(<${key_file} wc -l)"
_nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
split_scps=
for n in $(seq "${_nj}"); do
split_scps+=" ${_logdir}/keys.${n}.scp"
done
# shellcheck disable=SC2086
utils/split_scp.pl "${key_file}" ${split_scps}
_opts=
if [ -n "${inference_config}" ]; then
_opts+="--config ${inference_config} "
fi
${infer_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
python -m funasr.bin.asr_inference_launch \
--batch_size 1 \
--ngpu "${_ngpu}" \
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
--cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
--output_dir "${_logdir}"/output.JOB \
--mode bat \
${_opts}
for f in token token_int score text; do
if [ -f "${_logdir}/output.1/1best_recog/${f}" ]; then
for i in $(seq "${_nj}"); do
cat "${_logdir}/output.${i}/1best_recog/${f}"
done | sort -k1 >"${_dir}/${f}"
fi
done
python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
python utils/proce_text.py ${_data}/text ${_data}/text.proc
python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
cat ${_dir}/text.cer.txt
done
fi