From e422c6197b5bcada0429986500d8d5ca4ffcb3e4 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期三, 10 五月 2023 19:23:37 +0800
Subject: [PATCH] update repo
---
egs/librispeech_100h/conformer/run.sh | 37 ++++++++++++++++++++-----------------
1 files changed, 20 insertions(+), 17 deletions(-)
diff --git a/egs/librispeech_100h/conformer/run.sh b/egs/librispeech_100h/conformer/run.sh
index 93d1b46..a400788 100755
--- a/egs/librispeech_100h/conformer/run.sh
+++ b/egs/librispeech_100h/conformer/run.sh
@@ -3,8 +3,8 @@
. ./path.sh || exit 1;
# machines configuration
-CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
-gpu_num=8
+CUDA_VISIBLE_DEVICES="0,1"
+gpu_num=2
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
@@ -16,30 +16,26 @@
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
+type=sound
+scp=wav.scp
+stage=0
+stop_stage=0
# feature configuration
feats_dim=80
-sample_frequency=16000
-nj=100
-speed_perturb="0.9,1.0,1.1"
+nj=64
# data
-data_librispeech=
+raw_data=
+data_url=www.openslr.org/resources/12
# bpe model
nbpe=5000
bpemode=unigram
# exp tag
-tag=""
+tag="exp1"
. utils/parse_options.sh || exit 1;
@@ -54,8 +50,7 @@
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}"
+model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
inference_config=conf/decode_asr_transformer.yaml
#inference_config=conf/decode_asr_transformer_beam60_ctc0.3.yaml
@@ -73,11 +68,19 @@
_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; 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 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//-/_}
+ local/data_prep_librispeech.sh ${raw_data}/LibriSpeech/${x} ${feats_dir}/data/${x//-/_}
done
fi
--
Gitblit v1.9.1