speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update repo

Browse Source
This commit is contained in:
嘉渊 2023-05-26 10:06:51 +08:00
parent d748b861df
commit 450ed73340
7 changed files with 33 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
egs/aishell/conformer/run.sh
View File

@ -88,11 +88,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
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}
@ -130,7 +130,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
--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} \

6
egs/aishell/data2vec_paraformer_finetune/run.sh
View File

@ -91,11 +91,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
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}
@ -134,7 +134,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
--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} \

6
egs/aishell/data2vec_transformer_finetune/run.sh
View File

@ -91,11 +91,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
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}
@ -134,7 +134,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
--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} \

6
egs/aishell/paraformer/run.sh
View File

@ -88,11 +88,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
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}
@ -130,7 +130,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
--task_name asr \
--gpu_id $gpu_id \
--use_preprocessor true \
--token_type char \
--token_type $token_type \
--token_list $token_list \
--dataset_type small \
--data_dir ${feats_dir}/data \

6
egs/aishell/paraformerbert/run.sh
View File

@ -92,11 +92,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
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}
@ -141,7 +141,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
--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} \

6
egs/aishell/transformer/run.sh
View File

@ -88,11 +88,11 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
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}
@ -130,7 +130,7 @@ if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
--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} \

15
egs/wenetspeech/conformer/run.sh
View File

@ -84,3 +84,18 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
echo "stage 1: Feature and CMVN Generation"
utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$asr_config" --scale 0.1
fi
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/$token_type/
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