From 527667aa61942c6c3ba3460230b2041dbbdd9def Mon Sep 17 00:00:00 2001 From: speech_asr Date: Tue, 21 Mar 2023 17:33:26 +0800 Subject: [PATCH 1/4] update --- .../conf/decode_asr_transformer.yaml | 6 + .../conformer/conf/train_asr_conformer.yaml | 80 ++++++ .../conf/train_asr_conformer_uttnorm.yaml | 80 ++++++ .../conformer/local/data_prep_librispeech.sh | 58 ++++ egs/librispeech/conformer/path.sh | 5 + egs/librispeech/conformer/run.sh | 262 ++++++++++++++++++ egs/librispeech/conformer/utils | 1 + funasr/tasks/abs_task.py | 8 +- 8 files changed, 496 insertions(+), 4 deletions(-) create mode 100644 egs/librispeech/conformer/conf/decode_asr_transformer.yaml create mode 100644 egs/librispeech/conformer/conf/train_asr_conformer.yaml create mode 100644 egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml create mode 100755 egs/librispeech/conformer/local/data_prep_librispeech.sh create mode 100755 egs/librispeech/conformer/path.sh create mode 100755 egs/librispeech/conformer/run.sh create mode 120000 egs/librispeech/conformer/utils diff --git a/egs/librispeech/conformer/conf/decode_asr_transformer.yaml b/egs/librispeech/conformer/conf/decode_asr_transformer.yaml new file mode 100644 index 000000000..a147fa79d --- /dev/null +++ b/egs/librispeech/conformer/conf/decode_asr_transformer.yaml @@ -0,0 +1,6 @@ +beam_size: 10 +penalty: 0.0 +maxlenratio: 0.0 +minlenratio: 0.0 +ctc_weight: 0.5 +lm_weight: 0.7 diff --git a/egs/librispeech/conformer/conf/train_asr_conformer.yaml b/egs/librispeech/conformer/conf/train_asr_conformer.yaml new file mode 100644 index 000000000..93421f3a8 --- /dev/null +++ b/egs/librispeech/conformer/conf/train_asr_conformer.yaml @@ -0,0 +1,80 @@ +encoder: conformer +encoder_conf: + output_size: 512 + attention_heads: 8 + linear_units: 2048 + num_blocks: 12 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + attention_dropout_rate: 0.1 + input_layer: conv2d + normalize_before: true + macaron_style: true + rel_pos_type: latest + pos_enc_layer_type: rel_pos + selfattention_layer_type: rel_selfattn + activation_type: swish + use_cnn_module: true + cnn_module_kernel: 31 + +decoder: transformer +decoder_conf: + attention_heads: 8 + linear_units: 2048 + num_blocks: 6 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + self_attention_dropout_rate: 0.1 + src_attention_dropout_rate: 0.1 + +model_conf: + ctc_weight: 0.3 + lsm_weight: 0.1 + length_normalized_loss: false + +accum_grad: 2 +max_epoch: 50 +patience: none +init: none +best_model_criterion: +- - valid + - acc + - max +keep_nbest_models: 10 + +optim: adam +optim_conf: + lr: 0.0025 + weight_decay: 0.000001 +scheduler: warmuplr +scheduler_conf: + warmup_steps: 40000 + +specaug: specaug +specaug_conf: + apply_time_warp: true + time_warp_window: 5 + time_warp_mode: bicubic + apply_freq_mask: true + freq_mask_width_range: + - 0 + - 27 + num_freq_mask: 2 + apply_time_mask: true + time_mask_width_ratio_range: + - 0. + - 0.05 + num_time_mask: 10 + +dataset_conf: + shuffle: True + shuffle_conf: + shuffle_size: 2048 + sort_size: 500 + batch_conf: + batch_type: token + batch_size: 10000 + num_workers: 8 + +log_interval: 50 +normalize: None \ No newline at end of file diff --git a/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml b/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml new file mode 100644 index 000000000..ff1e265a9 --- /dev/null +++ b/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml @@ -0,0 +1,80 @@ +encoder: conformer +encoder_conf: + output_size: 512 + attention_heads: 8 + linear_units: 2048 + num_blocks: 12 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + attention_dropout_rate: 0.1 + input_layer: conv2d + normalize_before: true + macaron_style: true + rel_pos_type: latest + pos_enc_layer_type: rel_pos + selfattention_layer_type: rel_selfattn + activation_type: swish + use_cnn_module: true + cnn_module_kernel: 31 + +decoder: transformer +decoder_conf: + attention_heads: 8 + linear_units: 2048 + num_blocks: 6 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + self_attention_dropout_rate: 0.1 + src_attention_dropout_rate: 0.1 + +model_conf: + ctc_weight: 0.3 + lsm_weight: 0.1 + length_normalized_loss: false + +accum_grad: 2 +max_epoch: 50 +patience: none +init: none +best_model_criterion: +- - valid + - acc + - max +keep_nbest_models: 10 + +optim: adam +optim_conf: + lr: 0.0025 + weight_decay: 0.000001 +scheduler: warmuplr +scheduler_conf: + warmup_steps: 40000 + +specaug: specaug +specaug_conf: + apply_time_warp: true + time_warp_window: 5 + time_warp_mode: bicubic + apply_freq_mask: true + freq_mask_width_range: + - 0 + - 27 + num_freq_mask: 2 + apply_time_mask: true + time_mask_width_ratio_range: + - 0. + - 0.05 + num_time_mask: 10 + +dataset_conf: + shuffle: True + shuffle_conf: + shuffle_size: 2048 + sort_size: 500 + batch_conf: + batch_type: token + batch_size: 10000 + num_workers: 8 + +log_interval: 50 +normalize: utterance_mvn \ No newline at end of file diff --git a/egs/librispeech/conformer/local/data_prep_librispeech.sh b/egs/librispeech/conformer/local/data_prep_librispeech.sh new file mode 100755 index 000000000..c939b5f27 --- /dev/null +++ b/egs/librispeech/conformer/local/data_prep_librispeech.sh @@ -0,0 +1,58 @@ +#!/usr/bin/env bash + +# Copyright 2014 Vassil Panayotov +# 2014 Johns Hopkins University (author: Daniel Povey) +# Apache 2.0 + +if [ "$#" -ne 2 ]; then + echo "Usage: $0 " + echo "e.g.: $0 /export/a15/vpanayotov/data/LibriSpeech/dev-clean data/dev-clean" + exit 1 +fi + +src=$1 +dst=$2 + +# all utterances are FLAC compressed +if ! which flac >&/dev/null; then + echo "Please install 'flac' on ALL worker nodes!" + exit 1 +fi + +spk_file=$src/../SPEAKERS.TXT + +mkdir -p $dst || exit 1 + +[ ! -d $src ] && echo "$0: no such directory $src" && exit 1 +[ ! -f $spk_file ] && echo "$0: expected file $spk_file to exist" && exit 1 + + +wav_scp=$dst/wav.scp; [[ -f "$wav_scp" ]] && rm $wav_scp +trans=$dst/text; [[ -f "$trans" ]] && rm $trans + +for reader_dir in $(find -L $src -mindepth 1 -maxdepth 1 -type d | sort); do + reader=$(basename $reader_dir) + if ! [ $reader -eq $reader ]; then # not integer. + echo "$0: unexpected subdirectory name $reader" + exit 1 + fi + + for chapter_dir in $(find -L $reader_dir/ -mindepth 1 -maxdepth 1 -type d | sort); do + chapter=$(basename $chapter_dir) + if ! [ "$chapter" -eq "$chapter" ]; then + echo "$0: unexpected chapter-subdirectory name $chapter" + exit 1 + fi + + find -L $chapter_dir/ -iname "*.flac" | sort | xargs -I% basename % .flac | \ + awk -v "dir=$chapter_dir" '{printf "%s %s/%s.flac \n", $0, dir, $0}' >>$wav_scp|| exit 1 + + chapter_trans=$chapter_dir/${reader}-${chapter}.trans.txt + [ ! -f $chapter_trans ] && echo "$0: expected file $chapter_trans to exist" && exit 1 + cat $chapter_trans >>$trans + done +done + +echo "$0: successfully prepared data in $dst" + +exit 0 diff --git a/egs/librispeech/conformer/path.sh b/egs/librispeech/conformer/path.sh new file mode 100755 index 000000000..7972642d0 --- /dev/null +++ b/egs/librispeech/conformer/path.sh @@ -0,0 +1,5 @@ +export FUNASR_DIR=$PWD/../../.. + +# 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 diff --git a/egs/librispeech/conformer/run.sh b/egs/librispeech/conformer/run.sh new file mode 100755 index 000000000..93d1b463d --- /dev/null +++ b/egs/librispeech/conformer/run.sh @@ -0,0 +1,262 @@ +#!/usr/bin/env bash + +. ./path.sh || exit 1; + +# machines configuration +CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" +gpu_num=8 +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 +train_cmd=utils/run.pl +infer_cmd=utils/run.pl + +# general configuration +feats_dir="../DATA" #feature output dictionary +exp_dir="." +lang=en +dumpdir=dump/fbank +feats_type=fbank +token_type=bpe +dataset_type=large +scp=feats.scp +type=kaldi_ark +stage=3 +stop_stage=4 + +# feature configuration +feats_dim=80 +sample_frequency=16000 +nj=100 +speed_perturb="0.9,1.0,1.1" + +# data +data_librispeech= + +# bpe model +nbpe=5000 +bpemode=unigram + +# exp tag +tag="" + +. utils/parse_options.sh || exit 1; + +# Set bash to 'debug' mode, it will exit on : +# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands', +set -e +set -u +set -o pipefail + +train_set=train_960 +valid_set=dev +test_sets="test_clean test_other dev_clean dev_other" + +asr_config=conf/train_asr_conformer.yaml +#asr_config=conf/train_asr_conformer_uttnorm.yaml +model_dir="baseline_$(basename "${asr_config}" .yaml)_${feats_type}_${lang}_${token_type}_${tag}" + +inference_config=conf/decode_asr_transformer.yaml +#inference_config=conf/decode_asr_transformer_beam60_ctc0.3.yaml +inference_asr_model=valid.acc.ave_10best.pth + +# you can set gpu num for decoding here +gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default +ngpu=$(echo $gpuid_list | awk -F "," '{print NF}') + +if ${gpu_inference}; then + inference_nj=$[${ngpu}*${njob}] + _ngpu=1 +else + inference_nj=$njob + _ngpu=0 +fi + +if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then + echo "stage 0: Data preparation" + # Data preparation + for x in train-clean-100 train-clean-360 train-other-500 dev-clean dev-other test-clean test-other; do + local/data_prep_librispeech.sh ${data_librispeech}/LibriSpeech/${x} ${feats_dir}/data/${x//-/_} + done +fi + +feat_train_dir=${feats_dir}/${dumpdir}/$train_set; mkdir -p ${feat_train_dir} +feat_dev_clean_dir=${feats_dir}/${dumpdir}/dev_clean; mkdir -p ${feat_dev_clean_dir} +feat_dev_other_dir=${feats_dir}/${dumpdir}/dev_other; mkdir -p ${feat_dev_other_dir} +feat_test_clean_dir=${feats_dir}/${dumpdir}/test_clean; mkdir -p ${feat_test_clean_dir} +feat_test_other_dir=${feats_dir}/${dumpdir}/test_other; mkdir -p ${feat_test_other_dir} +feat_dev_dir=${feats_dir}/${dumpdir}/$valid_set; mkdir -p ${feat_dev_dir} +if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then + echo "stage 1: Feature Generation" + # compute fbank features + fbankdir=${feats_dir}/fbank + for x in dev_clean dev_other test_clean test_other; do + utils/compute_fbank.sh --cmd "$train_cmd" --nj 1 --max_lengths 3000 --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} \ + ${feats_dir}/data/${x} ${exp_dir}/exp/make_fbank/${x} ${fbankdir}/${x} + utils/fix_data_feat.sh ${fbankdir}/${x} + done + + mkdir ${feats_dir}/data/$train_set + train_sets="train_clean_100 train_clean_360 train_other_500" + for file in wav.scp text; do + ( for f in $train_sets; do cat $feats_dir/data/$f/$file; done ) | sort -k1 > $feats_dir/data/$train_set/$file || exit 1; + done + utils/compute_fbank.sh --cmd "$train_cmd" --nj $nj --max_lengths 3000 --feats_dim ${feats_dim} --sample_frequency ${sample_frequency} --speed_perturb ${speed_perturb} \ + ${feats_dir}/data/$train_set ${exp_dir}/exp/make_fbank/$train_set ${fbankdir}/$train_set + utils/fix_data_feat.sh ${fbankdir}/$train_set + + # compute global cmvn + utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} \ + ${fbankdir}/$train_set ${exp_dir}/exp/make_fbank/$train_set + + # apply cmvn + utils/apply_cmvn.sh --cmd "$train_cmd" --nj $nj \ + ${fbankdir}/$train_set ${fbankdir}/$train_set/cmvn.json ${exp_dir}/exp/make_fbank/$train_set ${feat_train_dir} + utils/apply_cmvn.sh --cmd "$train_cmd" --nj 1 \ + ${fbankdir}/dev_clean ${fbankdir}/$train_set/cmvn.json ${exp_dir}/exp/make_fbank/dev_clean ${feat_dev_clean_dir} + utils/apply_cmvn.sh --cmd "$train_cmd" --nj 1\ + ${fbankdir}/dev_other ${fbankdir}/$train_set/cmvn.json ${exp_dir}/exp/make_fbank/dev_other ${feat_dev_other_dir} + utils/apply_cmvn.sh --cmd "$train_cmd" --nj 1 \ + ${fbankdir}/test_clean ${fbankdir}/$train_set/cmvn.json ${exp_dir}/exp/make_fbank/test_clean ${feat_test_clean_dir} + utils/apply_cmvn.sh --cmd "$train_cmd" --nj 1 \ + ${fbankdir}/test_other ${fbankdir}/$train_set/cmvn.json ${exp_dir}/exp/make_fbank/test_other ${feat_test_other_dir} + + cp ${fbankdir}/$train_set/text ${fbankdir}/$train_set/speech_shape ${fbankdir}/$train_set/text_shape ${feat_train_dir} + cp ${fbankdir}/dev_clean/text ${fbankdir}/dev_clean/speech_shape ${fbankdir}/dev_clean/text_shape ${feat_dev_clean_dir} + cp ${fbankdir}/dev_other/text ${fbankdir}/dev_other/speech_shape ${fbankdir}/dev_other/text_shape ${feat_dev_other_dir} + cp ${fbankdir}/test_clean/text ${fbankdir}/test_clean/speech_shape ${fbankdir}/test_clean/text_shape ${feat_test_clean_dir} + cp ${fbankdir}/test_other/text ${fbankdir}/test_other/speech_shape ${fbankdir}/test_other/text_shape ${feat_test_other_dir} + + dev_sets="dev_clean dev_other" + for file in feats.scp text speech_shape text_shape; do + ( for f in $dev_sets; do cat $feats_dir/${dumpdir}/$f/$file; done ) | sort -k1 > $feat_dev_dir/$file || exit 1; + done + + #generate ark list + utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_train_dir} ${fbankdir}/${train_set} ${feat_train_dir} + utils/gen_ark_list.sh --cmd "$train_cmd" --nj $nj ${feat_dev_dir} ${fbankdir}/${valid_set} ${feat_dev_dir} +fi + +dict=${feats_dir}/data/lang_char/${train_set}_${bpemode}${nbpe}_units.txt +bpemodel=${feats_dir}/data/lang_char/${train_set}_${bpemode}${nbpe} +echo "dictionary: ${dict}" +if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then + ### Task dependent. You have to check non-linguistic symbols used in the corpus. + echo "stage 2: Dictionary and Json Data Preparation" + mkdir -p ${feats_dir}/data/lang_char/ + echo "" > ${dict} + echo "" >> ${dict} + echo "" >> ${dict} + cut -f 2- -d" " ${feats_dir}/data/${train_set}/text > ${feats_dir}/data/lang_char/input.txt + spm_train --input=${feats_dir}/data/lang_char/input.txt --vocab_size=${nbpe} --model_type=${bpemode} --model_prefix=${bpemodel} --input_sentence_size=100000000 + spm_encode --model=${bpemodel}.model --output_format=piece < ${feats_dir}/data/lang_char/input.txt | tr ' ' '\n' | sort | uniq | awk '{print $0}' >> ${dict} + echo "" >> ${dict} + wc -l ${dict} + + vocab_size=$(cat ${dict} | wc -l) + awk -v v=,${vocab_size} '{print $0v}' ${feat_train_dir}/text_shape > ${feat_train_dir}/text_shape.char + awk -v v=,${vocab_size} '{print $0v}' ${feat_dev_dir}/text_shape > ${feat_dev_dir}/text_shape.char + mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/$train_set + mkdir -p ${feats_dir}/asr_stats_fbank_zh_char/$valid_set + cp ${feat_train_dir}/speech_shape ${feat_train_dir}/text_shape ${feat_train_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/$train_set + cp ${feat_dev_dir}/speech_shape ${feat_dev_dir}/text_shape ${feat_dev_dir}/text_shape.char ${feats_dir}/asr_stats_fbank_zh_char/$valid_set +fi + + +# Training Stage +world_size=$gpu_num # run on one machine +if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then + echo "stage 3: 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 + if [ -f $INIT_FILE ];then + rm -f $INIT_FILE + fi + init_method=file://$(readlink -f $INIT_FILE) + echo "$0: init method is $init_method" + for ((i = 0; i < $gpu_num; ++i)); do + { + rank=$i + local_rank=$i + gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1]) + asr_train.py \ + --gpu_id $gpu_id \ + --use_preprocessor true \ + --split_with_space false \ + --bpemodel ${bpemodel}.model \ + --token_type $token_type \ + --dataset_type $dataset_type \ + --token_list $dict \ + --train_data_file $feats_dir/$dumpdir/${train_set}/ark_txt.scp \ + --valid_data_file $feats_dir/$dumpdir/${valid_set}/ark_txt.scp \ + --resume true \ + --output_dir ${exp_dir}/exp/${model_dir} \ + --config $asr_config \ + --input_size $feats_dim \ + --ngpu $gpu_num \ + --num_worker_count $count \ + --multiprocessing_distributed true \ + --dist_init_method $init_method \ + --dist_world_size $world_size \ + --dist_rank $rank \ + --local_rank $local_rank 1> ${exp_dir}/exp/${model_dir}/log/train.log.$i 2>&1 + } & + done + wait +fi + +# Testing Stage +if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then + echo "stage 4: 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}/${dumpdir}/${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}" \ + --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/compute_wer.py ${_data}/text ${_dir}/text ${_dir}/text.cer + tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt + cat ${_dir}/text.cer.txt + done +fi \ No newline at end of file diff --git a/egs/librispeech/conformer/utils b/egs/librispeech/conformer/utils new file mode 120000 index 000000000..fe070dd3a --- /dev/null +++ b/egs/librispeech/conformer/utils @@ -0,0 +1 @@ +../../aishell/transformer/utils \ No newline at end of file diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py index 3f20b4f4c..9f8fc83cf 100644 --- a/funasr/tasks/abs_task.py +++ b/funasr/tasks/abs_task.py @@ -1349,15 +1349,15 @@ class AbsTask(ABC): from funasr.datasets.large_datasets.build_dataloader import ArkDataLoader train_iter_factory = ArkDataLoader(args.train_data_file, args.token_list, args.dataset_conf, frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None, - seg_dict_file=args.seg_dict_file if hasattr(args, - "seg_dict_file") else None, + seg_dict_file=args.seg_dict_file if hasattr(args, "seg_dict_file") else None, punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None, + bpemodel_file=args.bpemodel if hasattr(args, "bpemodel") else None, mode="train") valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf, frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None, - seg_dict_file=args.seg_dict_file if hasattr(args, - "seg_dict_file") else None, + seg_dict_file=args.seg_dict_file if hasattr(args, "seg_dict_file") else None, punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None, + bpemodel_file=args.bpemodel if hasattr(args, "bpemodel") else None, mode="eval") elif args.dataset_type == "small": train_iter_factory = cls.build_iter_factory( From 4e7a8283bee800db1d5bb0f5b9414a11862a7772 Mon Sep 17 00:00:00 2001 From: speech_asr Date: Wed, 22 Mar 2023 16:00:42 +0800 Subject: [PATCH 2/4] update --- funasr/datasets/large_datasets/utils/tokenize.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py index 3f20c5f1f..d8ceff218 100644 --- a/funasr/datasets/large_datasets/utils/tokenize.py +++ b/funasr/datasets/large_datasets/utils/tokenize.py @@ -37,7 +37,7 @@ def tokenize(data, vad = -2 if bpe_tokenizer is not None: - text = bpe_tokenizer.text2tokens(text) + text = bpe_tokenizer.text2tokens("".join(text)) if seg_dict is not None: assert isinstance(seg_dict, dict) From 63cc47929c0b783e2b44f7d88dd56323dffd1449 Mon Sep 17 00:00:00 2001 From: speech_asr Date: Wed, 22 Mar 2023 17:01:14 +0800 Subject: [PATCH 3/4] update --- egs/librispeech/conformer/conf/train_asr_conformer.yaml | 2 +- egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/egs/librispeech/conformer/conf/train_asr_conformer.yaml b/egs/librispeech/conformer/conf/train_asr_conformer.yaml index 93421f3a8..68b127fe5 100644 --- a/egs/librispeech/conformer/conf/train_asr_conformer.yaml +++ b/egs/librispeech/conformer/conf/train_asr_conformer.yaml @@ -69,7 +69,7 @@ specaug_conf: dataset_conf: shuffle: True shuffle_conf: - shuffle_size: 2048 + shuffle_size: 1024 sort_size: 500 batch_conf: batch_type: token diff --git a/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml b/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml index ff1e265a9..16b7cc03f 100644 --- a/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml +++ b/egs/librispeech/conformer/conf/train_asr_conformer_uttnorm.yaml @@ -69,7 +69,7 @@ specaug_conf: dataset_conf: shuffle: True shuffle_conf: - shuffle_size: 2048 + shuffle_size: 1024 sort_size: 500 batch_conf: batch_type: token From ca2545a613dffcc6d255e00f39af82deaec39198 Mon Sep 17 00:00:00 2001 From: speech_asr Date: Wed, 29 Mar 2023 15:54:06 +0800 Subject: [PATCH 4/4] update --- funasr/train/trainer.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/funasr/train/trainer.py b/funasr/train/trainer.py index 4fbdcd94e..75f0921dc 100644 --- a/funasr/train/trainer.py +++ b/funasr/train/trainer.py @@ -579,9 +579,10 @@ class Trainer: reporter.measure_iter_time(iterator, "iter_time"), 1 ): assert isinstance(batch, dict), type(batch) - + if rank == 0 and hasattr(model.module, "num_updates"): - num_batch_updates = model.module.get_num_updates() + if hasattr(model, "num_updates") or (hasattr(model, "module") and hasattr(model.module, "num_updates")): + num_batch_updates = model.get_num_updates() if hasattr(model,"num_updates") else model.module.get_num_updates() if (num_batch_updates%batch_interval == 0) and (options.oss_bucket is not None) and options.use_pai: buffer = BytesIO() torch.save(model.state_dict(), buffer)