Update modelscope_models.md

chenmengzheAAA

2023-09-14 30c40c643c19f6e2ac8679fa76d09d0f9ceccc65

 egs/aishell2/data2vec_pretrain/run.sh

@@ -20,7 +20,6 @@
stop_stage=3

# feature configuration
feats_dim=80
nj=64

# data
@@ -42,7 +41,7 @@
valid_set=dev_ios

asr_config=conf/train_pretrain_transformer.yaml
model_dir="baseline_$(basename "${asr_config}" .yaml) _${lang}_${token_type}_${tag}"
model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"

if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
    echo "stage 0: Data preparation"
@@ -66,7 +65,7 @@

if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    echo "stage 1: Feature and CMVN Generation"
    utils/compute_cmvn.sh --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} ${feats_dir}/data/${train_set}
    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}_token_list/char/tokens.txt
@@ -109,13 +108,12 @@
                --train_set ${train_set} \
                --valid_set ${valid_set} \
                --data_file_names "wav.scp" \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
                --speed_perturb ${speed_perturb} \
                --dataset_type $dataset_type \
                --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 \