websocket 2pass bugfix

游雁

2023-05-19 219c2482ab755fbd4e49dfbdee91bf1a8a4ec49a

 egs/aishell/data2vec_transformer_finetune/run.sh

@@ -8,7 +8,7 @@
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=1
njob=5
train_cmd=utils/run.pl
infer_cmd=utils/run.pl

@@ -20,15 +20,15 @@
type=sound
scp=wav.scp
speed_perturb="0.9 1.0 1.1"
stage=3
stop_stage=4
stage=0
stop_stage=5

# feature configuration
feats_dim=80
nj=64

# data
raw_data=
raw_data=../raw_data
data_url=www.openslr.org/resources/33

# exp tag
@@ -52,8 +52,8 @@
asr_config=conf/train_asr_transformer_12e_6d_3072_768.yaml
model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"

inference_config=conf/decode_asr_transformer_noctc_1best.yaml
inference_asr_model=valid.acc.ave_10best.pb
inference_config=conf/decode_asr_transformer.yaml
inference_asr_model=valid.cer_ctc.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
@@ -106,11 +106,17 @@
    echo "<unk>" >> ${token_list}
fi

# Training Stage
# LM Training Stage
world_size=$gpu_num  # run on one machine
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
    echo "stage 3: Training"
     python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
    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"
    python utils/download_model.py  --model_name ${model_name}  # download pretrained model on ModelScope
    mkdir -p ${exp_dir}/exp/${model_dir}
    mkdir -p ${exp_dir}/exp/${model_dir}/log
    INIT_FILE=${exp_dir}/exp/${model_dir}/ddp_init
@@ -133,6 +139,7 @@
                --data_dir ${feats_dir}/data \
                --train_set ${train_set} \
                --valid_set ${valid_set} \
                --data_file_names "wav.scp,text" \
                --init_param ${init_param} \
                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
                --speed_perturb ${speed_perturb} \
@@ -151,8 +158,8 @@
fi

# Testing Stage
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
    echo "stage 4: Inference"
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 "${inference_config}" .yaml)"
@@ -189,7 +196,7 @@
                --asr_train_config "${asr_exp}"/config.yaml \
                --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
                --output_dir "${_logdir}"/output.JOB \
                --mode paraformer \
                --mode asr \
                ${_opts}

        for f in token token_int score text; do