From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
egs/aishell/conformer/run.sh | 111 +++++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 95 insertions(+), 16 deletions(-)
diff --git a/egs/aishell/conformer/run.sh b/egs/aishell/conformer/run.sh
index 05d35b7..e8643e9 100755
--- a/egs/aishell/conformer/run.sh
+++ b/egs/aishell/conformer/run.sh
@@ -3,12 +3,12 @@
. ./path.sh || exit 1;
# machines configuration
-CUDA_VISIBLE_DEVICES="2,3"
+CUDA_VISIBLE_DEVICES="0,1"
gpu_num=2
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=1
+njob=5
train_cmd=utils/run.pl
infer_cmd=utils/run.pl
@@ -16,20 +16,19 @@
feats_dir="../DATA" #feature output dictionary
exp_dir="."
lang=zh
-dumpdir=dump/fbank
-feats_type=fbank
token_type=char
-scp=wav.scp
type=sound
-stage=3
-stop_stage=3
+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=../raw_data
data_url=www.openslr.org/resources/33
# exp tag
@@ -48,7 +47,7 @@
test_sets="dev test"
asr_config=conf/train_asr_conformer.yaml
-model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}"
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
inference_asr_model=valid.acc.ave_10best.pb
@@ -86,14 +85,14 @@
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}
+ utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$asr_config" --scale 1.0
fi
-token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt
+token_list=${feats_dir}/data/${lang}_token_list/$token_type/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/
+ mkdir -p ${feats_dir}/data/${lang}_token_list/$token_type/
echo "make a dictionary"
echo "<blank>" > ${token_list}
@@ -104,10 +103,16 @@
echo "<unk>" >> ${token_list}
fi
-# Training Stage
+# LM Training Stage
world_size=$gpu_num # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
- echo "stage 3: Training"
+ echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+world_size=$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=${exp_dir}/exp/${model_dir}/ddp_init
@@ -125,12 +130,14 @@
--task_name asr \
--gpu_id $gpu_id \
--use_preprocessor true \
- --token_type char \
+ --token_type $token_type \
--token_list $token_list \
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --data_file_names "wav.scp,text" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
+ --speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
--config $asr_config \
@@ -143,4 +150,76 @@
} &
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/am.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 asr \
+ ${_opts}
+
+ for f in token token_int score text; do
+ if [ -f "${_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
+
+# Prepare files for ModelScope fine-tuning and inference
+if [ ${stage} -le 6 ] && [ ${stop_stage} -ge 6 ]; then
+ echo "stage 6: ModelScope Preparation"
+ cp ${feats_dir}/data/${train_set}/cmvn/am.mvn ${exp_dir}/exp/${model_dir}/am.mvn
+ vocab_size=$(cat ${token_list} | wc -l)
+ python utils/gen_modelscope_configuration.py \
+ --am_model_name $inference_asr_model \
+ --mode asr \
+ --model_name conformer \
+ --dataset aishell \
+ --output_dir $exp_dir/exp/$model_dir \
+ --vocab_size $vocab_size \
+ --tag $tag
fi
\ No newline at end of file
--
Gitblit v1.9.1