| egs/alimeeting/sa-asr/asr_local.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/alimeeting/sa-asr/local/alimeeting_data_prep.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 | |
| egs/alimeeting/sa-asr/path.sh | ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史 |
egs/alimeeting/sa-asr/asr_local.sh
@@ -1153,10 +1153,10 @@ mkdir -p ${sa_asr_exp}/log INIT_FILE=${sa_asr_exp}/ddp_init if [ ! -f "exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pth" ]; then if [ ! -f "exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pb" ]; then # download xvector extractor model file python local/download_xvector_model.py exp log "Successfully download the pretrained xvector extractor to exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pth" log "Successfully download the pretrained xvector extractor to exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pb" fi if [ -f $INIT_FILE ];then @@ -1195,8 +1195,8 @@ --init_param "${asr_exp}/valid.acc.ave.pb:decoder.decoders.3:decoder.decoder4.2" \ --init_param "${asr_exp}/valid.acc.ave.pb:decoder.decoders.4:decoder.decoder4.3" \ --init_param "${asr_exp}/valid.acc.ave.pb:decoder.decoders.5:decoder.decoder4.4" \ --init_param "exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pth:encoder:spk_encoder" \ --init_param "exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pth:decoder:spk_encoder:decoder.output_dense" \ --init_param "exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pb:encoder:spk_encoder" \ --init_param "exp/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/sv.pb:decoder:spk_encoder:decoder.output_dense" \ --valid_data_path_and_name_and_type "${_asr_valid_dir}/${_scp},speech,${_type}" \ --valid_data_path_and_name_and_type "${_asr_valid_dir}/text,text,text" \ --valid_data_path_and_name_and_type "${_asr_valid_dir}/oracle_profile_nopadding.scp,profile,npy" \ egs/alimeeting/sa-asr/local/alimeeting_data_prep.sh
@@ -61,9 +61,9 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then log "stage 1:process alimeeting near dir" find -L $near_raw_dir/audio_dir -iname "*.wav" > $near_dir/wavlist find -L $near_raw_dir/audio_dir -iname "*.wav" | sort > $near_dir/wavlist awk -F '/' '{print $NF}' $near_dir/wavlist | awk -F '.' '{print $1}' > $near_dir/uttid find -L $near_raw_dir/textgrid_dir -iname "*.TextGrid" > $near_dir/textgrid.flist find -L $near_raw_dir/textgrid_dir -iname "*.TextGrid" | sort > $near_dir/textgrid.flist n1_wav=$(wc -l < $near_dir/wavlist) n2_text=$(wc -l < $near_dir/textgrid.flist) log near file found $n1_wav wav and $n2_text text. @@ -90,9 +90,9 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then log "stage 2:process alimeeting far dir" find -L $far_raw_dir/audio_dir -iname "*.wav" > $far_dir/wavlist find -L $far_raw_dir/audio_dir -iname "*.wav" | sort > $far_dir/wavlist awk -F '/' '{print $NF}' $far_dir/wavlist | awk -F '.' '{print $1}' > $far_dir/uttid find -L $far_raw_dir/textgrid_dir -iname "*.TextGrid" > $far_dir/textgrid.flist find -L $far_raw_dir/textgrid_dir -iname "*.TextGrid" | sort > $far_dir/textgrid.flist n1_wav=$(wc -l < $far_dir/wavlist) n2_text=$(wc -l < $far_dir/textgrid.flist) log far file found $n1_wav wav and $n2_text text. @@ -120,7 +120,8 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then log "stage 3: finali data process" local/fix_data_dir.sh $near_dir local/fix_data_dir.sh $far_dir local/copy_data_dir.sh $near_dir data/${tgt}_Ali_near local/copy_data_dir.sh $far_dir data/${tgt}_Ali_far
@@ -2,4 +2,4 @@ # NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C export PYTHONIOENCODING=UTF-8 export PATH=$FUNASR_DIR/funasr/bin:$PATH export PATH=$FUNASR_DIR/funasr/bin:./utils:$PATH
