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/paraformerbert/run.sh | 52 ++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 38 insertions(+), 14 deletions(-)
diff --git a/egs/aishell/paraformerbert/run.sh b/egs/aishell/paraformerbert/run.sh
index e0245f3..efc831f 100755
--- a/egs/aishell/paraformerbert/run.sh
+++ b/egs/aishell/paraformerbert/run.sh
@@ -20,8 +20,8 @@
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
-stage=3
-stop_stage=4
+stage=0
+stop_stage=5
skip_extract_embed=false
bert_model_name="bert-base-chinese"
@@ -31,7 +31,7 @@
nj=64
# data
-raw_data=
+raw_data=../raw_data
data_url=www.openslr.org/resources/33
# exp tag
@@ -89,14 +89,14 @@
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}
@@ -107,15 +107,22 @@
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 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: ASR Training"
if ! "${skip_extract_embed}"; then
echo "extract embeddings..."
local/extract_embeds.sh \
--bert_model_name ${bert_model_name} \
- --raw_dataset_path ${feats_dir}
+ --raw_dataset_path ${feats_dir} \
+ --nj $nj
fi
mkdir -p ${exp_dir}/exp/${model_dir}
mkdir -p ${exp_dir}/exp/${model_dir}/log
@@ -134,12 +141,13 @@
--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,embeds.scp" \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -156,8 +164,8 @@
fi
# Testing Stage
-if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
- echo "stage 4: Inference"
+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 "${inference_config}" .yaml)"
@@ -168,7 +176,7 @@
exit 0
fi
mkdir -p "${_logdir}"
- _data="${feats_dir}/${dumpdir}/${dset}"
+ _data="${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")
@@ -189,6 +197,7 @@
--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}" \
@@ -211,3 +220,18 @@
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 paraformer \
+ --model_name paraformer_bert \
+ --dataset aishell \
+ --output_dir $exp_dir/exp/$model_dir \
+ --vocab_size $vocab_size \
+ --nat _nat \
+ --tag $tag
+fi
\ No newline at end of file
--
Gitblit v1.9.1