| egs/aishell/data2vec_transformer_finetune/run.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/aishell/paraformerbert/local/aishell_data_prep.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/aishell/paraformerbert/local/download_and_untar.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/aishell/paraformerbert/run.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
egs/aishell/data2vec_transformer_finetune/run.sh
@@ -53,7 +53,7 @@ model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}" inference_config=conf/decode_asr_transformer.yaml inference_asr_model=valid.acc.ave_10best.pb inference_asr_model=valid.cer_ctc.ave_10best.pb # you can set gpu num for decoding here gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default @@ -189,7 +189,7 @@ --asr_train_config "${asr_exp}"/config.yaml \ --asr_model_file "${asr_exp}"/"${inference_asr_model}" \ --output_dir "${_logdir}"/output.JOB \ --mode paraformer \ --mode asr \ ${_opts} for f in token token_int score text; do egs/aishell/paraformerbert/local/aishell_data_prep.sh
@@ -5,19 +5,20 @@ #. ./path.sh || exit 1; if [ $# != 2 ]; then echo "Usage: $0 <audio-path> <text-path>" echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript" if [ $# != 3 ]; then echo "Usage: $0 <audio-path> <text-path> <output-path>" echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data" exit 1; fi aishell_audio_dir=$1 aishell_text=$2/aishell_transcript_v0.8.txt output_dir=$3 train_dir=data/local/train dev_dir=data/local/dev test_dir=data/local/test tmp_dir=data/local/tmp train_dir=$output_dir/data/local/train dev_dir=$output_dir/data/local/dev test_dir=$output_dir/data/local/test tmp_dir=$output_dir/data/local/tmp mkdir -p $train_dir mkdir -p $dev_dir @@ -53,12 +54,12 @@ sort -u $dir/transcripts.txt > $dir/text done mkdir -p data/train data/dev data/test mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test for f in wav.scp text; do cp $train_dir/$f data/train/$f || exit 1; cp $dev_dir/$f data/dev/$f || exit 1; cp $test_dir/$f data/test/$f || exit 1; cp $train_dir/$f $output_dir/data/train/$f || exit 1; cp $dev_dir/$f $output_dir/data/dev/$f || exit 1; cp $test_dir/$f $output_dir/data/test/$f || exit 1; done echo "$0: AISHELL data preparation succeeded" egs/aishell/paraformerbert/local/download_and_untar.sh
New file @@ -0,0 +1,105 @@ #!/usr/bin/env bash # Copyright 2014 Johns Hopkins University (author: Daniel Povey) # 2017 Xingyu Na # Apache 2.0 remove_archive=false if [ "$1" == --remove-archive ]; then remove_archive=true shift fi if [ $# -ne 3 ]; then echo "Usage: $0 [--remove-archive] <data-base> <url-base> <corpus-part>" echo "e.g.: $0 /export/a05/xna/data www.openslr.org/resources/33 data_aishell" echo "With --remove-archive it will remove the archive after successfully un-tarring it." echo "<corpus-part> can be one of: data_aishell, resource_aishell." fi data=$1 url=$2 part=$3 if [ ! -d "$data" ]; then echo "$0: no such directory $data" exit 1; fi part_ok=false list="data_aishell resource_aishell" for x in $list; do if [ "$part" == $x ]; then part_ok=true; fi done if ! $part_ok; then echo "$0: expected <corpus-part> to be one of $list, but got '$part'" exit 1; fi if [ -z "$url" ]; then echo "$0: empty URL base." exit 1; fi if [ -f $data/$part/.complete ]; then echo "$0: data part $part was already successfully extracted, nothing to do." exit 0; fi # sizes of the archive files in bytes. sizes="15582913665 1246920" if [ -f $data/$part.tgz ]; then size=$(/bin/ls -l $data/$part.tgz | awk '{print $5}') size_ok=false for s in $sizes; do if [ $s == $size ]; then size_ok=true; fi; done if ! $size_ok; then echo "$0: removing existing file $data/$part.tgz because its size in bytes $size" echo "does not equal the size of one of the archives." rm $data/$part.tgz else echo "$data/$part.tgz exists and appears to be complete." fi fi if [ ! -f $data/$part.tgz ]; then if ! command -v wget >/dev/null; then echo "$0: wget is not installed." exit 1; fi full_url=$url/$part.tgz echo "$0: downloading data from $full_url. This may take some time, please be patient." cd $data || exit 1 if ! wget --no-check-certificate $full_url; then echo "$0: error executing wget $full_url" exit 1; fi fi cd $data || exit 1 if ! tar -xvzf $part.tgz; then echo "$0: error un-tarring archive $data/$part.tgz" exit 1; fi touch $data/$part/.complete if [ $part == "data_aishell" ]; then cd $data/$part/wav || exit 1 for wav in ./*.tar.gz; do echo "Extracting wav from $wav" tar -zxf $wav && rm $wav done fi echo "$0: Successfully downloaded and un-tarred $data/$part.tgz" if $remove_archive; then echo "$0: removing $data/$part.tgz file since --remove-archive option was supplied." rm $data/$part.tgz fi exit 0; egs/aishell/paraformerbert/run.sh
@@ -8,7 +8,7 @@ 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 njob=1 train_cmd=utils/run.pl infer_cmd=utils/run.pl