From d86e39895ad0ab465b697d79b1bff806c73bb3fe Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 07 八月 2023 09:43:52 +0800
Subject: [PATCH] update repo
---
egs/librispeech/e_branchformer/local/data_prep.sh | 58 +++++
egs/librispeech/e_branchformer/conf/decode_asr_transformer_beam10_ctc0.3.yaml | 6
egs/librispeech/e_branchformer/local/download_and_untar.sh | 97 ++++++++
egs/librispeech/e_branchformer/local/spm_train.py | 12 +
egs/librispeech/e_branchformer/run.sh | 223 ++++++++++++++++++++
egs/librispeech/e_branchformer/local/spm_encode.py | 98 ++++++++
egs/librispeech/e_branchformer/path.sh | 5
egs/librispeech/e_branchformer/utils | 1
egs/librispeech/e_branchformer/conf/train_asr_e_branchformer.yaml | 105 +++++++++
9 files changed, 605 insertions(+), 0 deletions(-)
diff --git a/egs/librispeech/e_branchformer/conf/decode_asr_transformer_beam10_ctc0.3.yaml b/egs/librispeech/e_branchformer/conf/decode_asr_transformer_beam10_ctc0.3.yaml
new file mode 100644
index 0000000..62745de
--- /dev/null
+++ b/egs/librispeech/e_branchformer/conf/decode_asr_transformer_beam10_ctc0.3.yaml
@@ -0,0 +1,6 @@
+beam_size: 10
+penalty: 0.0
+maxlenratio: 0.0
+minlenratio: 0.0
+ctc_weight: 0.3
+lm_weight: 0.0
diff --git a/egs/librispeech/e_branchformer/conf/train_asr_e_branchformer.yaml b/egs/librispeech/e_branchformer/conf/train_asr_e_branchformer.yaml
new file mode 100644
index 0000000..c3607ae
--- /dev/null
+++ b/egs/librispeech/e_branchformer/conf/train_asr_e_branchformer.yaml
@@ -0,0 +1,105 @@
+# network architecture
+# encoder related
+encoder: e_branchformer
+encoder_conf:
+ output_size: 512
+ attention_heads: 8
+ attention_layer_type: rel_selfattn
+ pos_enc_layer_type: rel_pos
+ rel_pos_type: latest
+ cgmlp_linear_units: 3072
+ cgmlp_conv_kernel: 31
+ use_linear_after_conv: false
+ gate_activation: identity
+ num_blocks: 17
+ dropout_rate: 0.1
+ positional_dropout_rate: 0.1
+ attention_dropout_rate: 0.1
+ input_layer: conv2d
+ layer_drop_rate: 0.1
+ linear_units: 1024
+ positionwise_layer_type: linear
+ macaron_ffn: true
+ use_ffn: true
+ merge_conv_kernel: 31
+
+# decoder related
+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
+ layer_drop_rate: 0.2
+
+# frontend related
+frontend: wav_frontend
+frontend_conf:
+ fs: 16000
+ window: hamming
+ n_mels: 80
+ frame_length: 25
+ frame_shift: 10
+ lfr_m: 1
+ lfr_n: 1
+
+# hybrid CTC/attention
+model_conf:
+ ctc_weight: 0.3
+ lsm_weight: 0.1 # label smoothing option
+ length_normalized_loss: false
+
+# optimization related
+accum_grad: 2
+grad_clip: 5
+max_epoch: 240
+val_scheduler_criterion:
+ - valid
+ - acc
+best_model_criterion:
+- - valid
+ - acc
+ - max
+keep_nbest_models: 10
+
+optim: adam
+optim_conf:
+ lr: 0.002
+ 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:
+ data_names: speech,text
+ data_types: sound,text
+ shuffle: True
+ shuffle_conf:
+ shuffle_size: 2048
+ sort_size: 500
+ batch_conf:
+ batch_type: token
+ batch_size: 30000
+ num_workers: 8
+
+log_interval: 50
+normalize: None
\ No newline at end of file
diff --git a/egs/librispeech/e_branchformer/local/data_prep.sh b/egs/librispeech/e_branchformer/local/data_prep.sh
new file mode 100755
index 0000000..c939b5f
--- /dev/null
+++ b/egs/librispeech/e_branchformer/local/data_prep.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 <src-dir> <dst-dir>"
+ 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/e_branchformer/local/download_and_untar.sh b/egs/librispeech/e_branchformer/local/download_and_untar.sh
new file mode 100755
index 0000000..fe322e4
--- /dev/null
+++ b/egs/librispeech/e_branchformer/local/download_and_untar.sh
@@ -0,0 +1,97 @@
+#!/usr/bin/env bash
+
+# Copyright 2014 Johns Hopkins University (author: Daniel Povey)
+# 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/a15/vpanayotov/data www.openslr.org/resources/11 dev-clean"
+ echo "With --remove-archive it will remove the archive after successfully un-tarring it."
+ echo "<corpus-part> can be one of: dev-clean, test-clean, dev-other, test-other,"
+ echo " train-clean-100, train-clean-360, train-other-500."
+ exit 1
+fi
+
+data=$1
+url=$2
+part=$3
+
+if [ ! -d "$data" ]; then
+ echo "$0: no such directory $data"
+ exit 1
+fi
+
+part_ok=false
+list="dev-clean test-clean dev-other test-other train-clean-100 train-clean-360 train-other-500"
+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 $data/LibriSpeech/$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. This is some older versions.
+sizes_old="371012589 347390293 379743611 361838298 6420417880 23082659865 30626749128"
+# sizes_new is the archive file sizes of the final release. Some of these sizes are of
+# things we probably won't download.
+sizes_new="337926286 314305928 695964615 297279345 87960560420 33373768 346663984 328757843 6387309499 23049477885 30593501606"
+
+if [ -f $data/$part.tar.gz ]; then
+ size=$(/bin/ls -l $data/$part.tar.gz | awk '{print $5}')
+ size_ok=false
+ for s in $sizes_old $sizes_new; do if [ $s == $size ]; then size_ok=true; fi; done
+ if ! $size_ok; then
+ echo "$0: removing existing file $data/$part.tar.gz because its size in bytes $size"
+ echo "does not equal the size of one of the archives."
+ rm $data/$part.tar.gz
+ else
+ echo "$data/$part.tar.gz exists and appears to be complete."
+ fi
+fi
+
+if [ ! -f $data/$part.tar.gz ]; then
+ if ! which wget >/dev/null; then
+ echo "$0: wget is not installed."
+ exit 1
+ fi
+ full_url=$url/$part.tar.gz
+ echo "$0: downloading data from $full_url. This may take some time, please be patient."
+
+ if ! wget -P $data --no-check-certificate $full_url; then
+ echo "$0: error executing wget $full_url"
+ exit 1
+ fi
+fi
+
+if ! tar -C $data -xvzf $data/$part.tar.gz; then
+ echo "$0: error un-tarring archive $data/$part.tar.gz"
+ exit 1
+fi
+
+touch $data/LibriSpeech/$part/.complete
+
+echo "$0: Successfully downloaded and un-tarred $data/$part.tar.gz"
+
+if $remove_archive; then
+ echo "$0: removing $data/$part.tar.gz file since --remove-archive option was supplied."
+ rm $data/$part.tar.gz
+fi
diff --git a/egs/librispeech/e_branchformer/local/spm_encode.py b/egs/librispeech/e_branchformer/local/spm_encode.py
new file mode 100755
index 0000000..9e1c15f
--- /dev/null
+++ b/egs/librispeech/e_branchformer/local/spm_encode.py
@@ -0,0 +1,98 @@
+#!/usr/bin/env python
+# Copyright (c) Facebook, Inc. and its affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in
+# https://github.com/pytorch/fairseq/blob/master/LICENSE
+
+
+import argparse
+import contextlib
+import sys
+
+import sentencepiece as spm
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument("--model", required=True,
+ help="sentencepiece model to use for encoding")
+ parser.add_argument("--inputs", nargs="+", default=['-'],
+ help="input files to filter/encode")
+ parser.add_argument("--outputs", nargs="+", default=['-'],
+ help="path to save encoded outputs")
+ parser.add_argument("--output_format", choices=["piece", "id"], default="piece")
+ parser.add_argument("--min-len", type=int, metavar="N",
+ help="filter sentence pairs with fewer than N tokens")
+ parser.add_argument("--max-len", type=int, metavar="N",
+ help="filter sentence pairs with more than N tokens")
+ args = parser.parse_args()
+
+ assert len(args.inputs) == len(args.outputs), \
+ "number of input and output paths should match"
+
+ sp = spm.SentencePieceProcessor()
+ sp.Load(args.model)
+
+ if args.output_format == "piece":
+ def encode(l):
+ return sp.EncodeAsPieces(l)
+ elif args.output_format == "id":
+ def encode(l):
+ return list(map(str, sp.EncodeAsIds(l)))
+ else:
+ raise NotImplementedError
+
+ if args.min_len is not None or args.max_len is not None:
+ def valid(line):
+ return (
+ (args.min_len is None or len(line) >= args.min_len) and
+ (args.max_len is None or len(line) <= args.max_len)
+ )
+ else:
+ def valid(lines):
+ return True
+
+ with contextlib.ExitStack() as stack:
+ inputs = [
+ stack.enter_context(open(input, "r", encoding="utf-8"))
+ if input != "-" else sys.stdin
+ for input in args.inputs
+ ]
+ outputs = [
+ stack.enter_context(open(output, "w", encoding="utf-8"))
+ if output != "-" else sys.stdout
+ for output in args.outputs
+ ]
+
+ stats = {
+ "num_empty": 0,
+ "num_filtered": 0,
+ }
+
+ def encode_line(line):
+ line = line.strip()
+ if len(line) > 0:
+ line = encode(line)
+ if valid(line):
+ return line
+ else:
+ stats["num_filtered"] += 1
+ else:
+ stats["num_empty"] += 1
+ return None
+
+ for i, lines in enumerate(zip(*inputs), start=1):
+ enc_lines = list(map(encode_line, lines))
+ if not any(enc_line is None for enc_line in enc_lines):
+ for enc_line, output_h in zip(enc_lines, outputs):
+ print(" ".join(enc_line), file=output_h)
+ if i % 10000 == 0:
+ print("processed {} lines".format(i), file=sys.stderr)
+
+ print("skipped {} empty lines".format(stats["num_empty"]), file=sys.stderr)
+ print("filtered {} lines".format(stats["num_filtered"]), file=sys.stderr)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/egs/librispeech/e_branchformer/local/spm_train.py b/egs/librispeech/e_branchformer/local/spm_train.py
new file mode 100755
index 0000000..134a0b1
--- /dev/null
+++ b/egs/librispeech/e_branchformer/local/spm_train.py
@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+# Copyright (c) Facebook, Inc. and its affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in the
+# https://github.com/pytorch/fairseq/blob/master/LICENSE
+import sys
+
+import sentencepiece as spm
+
+if __name__ == "__main__":
+ spm.SentencePieceTrainer.Train(" ".join(sys.argv[1:]))
diff --git a/egs/librispeech/e_branchformer/path.sh b/egs/librispeech/e_branchformer/path.sh
new file mode 100755
index 0000000..7972642
--- /dev/null
+++ b/egs/librispeech/e_branchformer/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:$PATH
diff --git a/egs/librispeech/e_branchformer/run.sh b/egs/librispeech/e_branchformer/run.sh
new file mode 100755
index 0000000..f1ffa0d
--- /dev/null
+++ b/egs/librispeech/e_branchformer/run.sh
@@ -0,0 +1,223 @@
+#!/usr/bin/env bash
+
+. ./path.sh || exit 1;
+
+# machines configuration
+CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
+gpu_num=8
+count=1
+gpu_inference=true # Whether to perform gpu decoding, set false for cpu decoding
+# for gpu decoding, inference_nj=ngpu*njob; for cpu decoding, inference_nj=njob
+njob=5
+train_cmd=utils/run.pl
+infer_cmd=utils/run.pl
+
+# general configuration
+feats_dir="../DATA" #feature output dictionary
+exp_dir="."
+lang=en
+token_type=bpe
+type=sound
+scp=wav.scp
+speed_perturb="0.9 1.0 1.1"
+stage=0
+stop_stage=5
+
+# feature configuration
+feats_dim=80
+nj=64
+
+# data
+raw_data=
+data_url=www.openslr.org/resources/12
+
+# bpe model
+nbpe=5000
+bpemode=unigram
+
+# exp tag
+tag="exp1"
+
+. utils/parse_options.sh || exit 1;
+
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+train_set=train_960
+valid_set=dev
+test_sets="test_clean test_other dev_clean dev_other"
+
+asr_config=conf/train_asr_e_branchformer.yaml
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
+
+inference_config=conf/decode_asr_transformer_beam10_ctc0.3.yaml
+inference_asr_model=valid.acc.ave_10best.pb
+
+# you can set gpu num for decoding here
+gpuid_list=$CUDA_VISIBLE_DEVICES # set gpus for decoding, the same as training stage by default
+ngpu=$(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 -1 ] && [ ${stop_stage} -ge -1 ]; then
+ echo "stage -1: Data Download"
+ for part in dev-clean test-clean dev-other test-other train-clean-100 train-clean-360 train-other-500; do
+ local/download_and_untar.sh ${raw_data} ${data_url} ${part}
+ done
+fi
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+ echo "stage 0: Data preparation"
+ # Data preparation
+ for x in dev-clean dev-other test-clean test-other train-clean-100 train-clean-360 train-other-500; do
+ local/data_prep.sh ${raw_data}/LibriSpeech/${x} ${feats_dir}/data/${x//-/_}
+ done
+ mkdir $feats_dir/data/$valid_set
+ dev_sets="dev_clean dev_other"
+ for file in wav.scp text; do
+ ( for f in $dev_sets; do cat $feats_dir/data/$f/$file; done ) | sort -k1 > $feats_dir/data/$valid_set/$file || exit 1;
+ 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
+fi
+
+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 1.0
+fi
+
+token_list=${feats_dir}/data/lang_char/${train_set}_${bpemode}${nbpe}_units.txt
+bpemodel=${feats_dir}/data/lang_char/${train_set}_${bpemode}${nbpe}
+echo "dictionary: ${token_list}"
+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 "<blank>" > ${token_list}
+ echo "<s>" >> ${token_list}
+ echo "</s>" >> ${token_list}
+ cut -f 2- -d" " ${feats_dir}/data/${train_set}/text > ${feats_dir}/data/lang_char/input.txt
+ local/spm_train.py --input=${feats_dir}/data/lang_char/input.txt --vocab_size=${nbpe} --model_type=${bpemode} --model_prefix=${bpemodel} --input_sentence_size=100000000
+ local/spm_encode.py --model=${bpemodel}.model --output_format=piece < ${feats_dir}/data/lang_char/input.txt | tr ' ' '\n' | sort | uniq | awk '{print $0}' >> ${token_list}
+ echo "<unk>" >> ${token_list}
+fi
+
+# LM Training Stage
+world_size=$gpu_num # run on one machine
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+ echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+world_size=$gpu_num # run on one machine
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: ASR Training"
+ 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])
+ train.py \
+ --task_name asr \
+ --gpu_id $gpu_id \
+ --use_preprocessor true \
+ --split_with_space false \
+ --bpemodel ${bpemodel}.model \
+ --token_type $token_type \
+ --token_list $token_list \
+ --dataset_type large \
+ --data_dir ${feats_dir}/data \
+ --train_set ${train_set} \
+ --valid_set ${valid_set} \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
+ --speed_perturb ${speed_perturb} \
+ --resume true \
+ --output_dir ${exp_dir}/exp/${model_dir} \
+ --config $asr_config \
+ --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 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 "${inference_config}" .yaml)"
+ _dir="${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}/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")
+ 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}" \
+ --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}" \
+ --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/e_branchformer/utils b/egs/librispeech/e_branchformer/utils
new file mode 120000
index 0000000..fe070dd
--- /dev/null
+++ b/egs/librispeech/e_branchformer/utils
@@ -0,0 +1 @@
+../../aishell/transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1