update repo

嘉渊

2023-05-24 606ce7633124e30badab86b19a07897da78b4540

update repo

 egs/aishell/conformer/run.sh

@@ -85,7 +85,7 @@

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 ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt

 egs/aishell/data2vec_paraformer_finetune/run.sh

@@ -88,7 +88,7 @@

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 ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt

 egs/aishell/data2vec_transformer_finetune/run.sh

@@ -88,7 +88,7 @@

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 ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt

 egs/aishell/paraformer/run.sh

@@ -85,7 +85,7 @@

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 ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt

 egs/aishell/paraformerbert/run.sh

@@ -89,7 +89,7 @@

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 ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt

 egs/aishell/transformer/run.sh

@@ -85,7 +85,7 @@

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 ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config $asr_config --scale 1.0
fi

token_list=${feats_dir}/data/${lang}_token_list/char/tokens.txt

 egs/aishell/transformer/utils/compute_cmvn.py

@@ -5,6 +5,7 @@
import numpy as np
import torchaudio
import torchaudio.compliance.kaldi as kaldi
import yaml


def get_parser():
@@ -24,6 +25,11 @@
        required=True,
        type=str,
        help="the path of wav scps",
    )
    parser.add_argument(
        "--config",
        type=str,
        help="the config file for computing cmvn",
    )
    parser.add_argument(
        "--idx",
@@ -82,11 +88,27 @@
    #         mean_stats += np.sum(mat, axis=0)
    #         var_stats += np.sum(np.square(mat), axis=0)
    #         total_frames += mat.shape[0]

    with open(args.config) as f:
        configs = yaml.safe_load(f)
        frontend_configs = configs.get("frontend_conf", {})
        num_mel_bins = frontend_configs.get("n_mels", 80)
        frame_length = frontend_configs.get("frame_length", 25)
        frame_shift = frontend_configs.get("frame_shift", 10)
        window_type = frontend_configs.get("window", "hamming")
        resample_rate = frontend_configs.get("fs", 16000)
        assert num_mel_bins == args.dim

    with open(wav_scp_file) as f:
        lines = f.readlines()
        for line in lines:
            _, wav_file = line.strip().split()
            fbank = compute_fbank(wav_file, num_mel_bins=args.dim)
            fbank = compute_fbank(wav_file,
                                  num_mel_bins=args.dim,
                                  frame_length=frame_length,
                                  frame_shift=frame_shift,
                                  resample_rate=resample_rate,
                                  window_type=window_type)
            mean_stats += np.sum(fbank, axis=0)
            var_stats += np.sum(np.square(fbank), axis=0)
            total_frames += fbank.shape[0]

 egs/aishell/transformer/utils/compute_cmvn.sh

@@ -2,15 +2,19 @@

. ./path.sh || exit 1;
# Begin configuration section.
fbankdir=$1
nj=32
cmd=./utils/run.pl
feats_dim=80
config=
scale=1.0

echo "$0 $@"

. utils/parse_options.sh || exit 1;

fbankdir=$1
# shellcheck disable=SC2046
head -n $(awk -v lines="$(wc -l < ${fbankdir}/wav.scp)" -v scale="$scale" 'BEGIN { printf "%.0f\n", lines*scale }') ${fbankdir}/wav.scp > ${fbankdir}/wav.scp.scale

split_dir=${fbankdir}/cmvn/split_${nj};
mkdir -p $split_dir
@@ -18,14 +22,15 @@
for n in $(seq $nj); do
    split_scps="$split_scps $split_dir/wav.$n.scp"
done
utils/split_scp.pl ${fbankdir}/wav.scp $split_scps || exit 1;
utils/split_scp.pl ${fbankdir}/wav.scp.scale $split_scps || exit 1;

logdir=${fbankdir}/cmvn/log
$cmd JOB=1:$nj $logdir/cmvn.JOB.log \
    python utils/compute_cmvn.py \
      --dim ${feats_dim} \
      --wav_path $split_dir \
      --idx JOB
      --config $config \
      --idx JOB \

python utils/combine_cmvn_file.py --dim ${feats_dim} --cmvn_dir $split_dir --nj $nj --output_dir ${fbankdir}/cmvn