paraformer streaming bugfix

游雁

2024-03-18 cbe2ea7e07cbf364827bd89cefc42b3f643ea3be

 examples/aishell/conformer/run.sh

@@ -14,10 +14,10 @@
# feature configuration
nj=32

inference_device="cuda" #"cpu"
inference_device="cuda" #"cpu", "cuda:0", "cuda:1"
inference_checkpoint="model.pt"
inference_scp="wav.scp"
inference_batch_size=32
inference_batch_size=1

# data
raw_data=../raw_data
@@ -142,8 +142,9 @@

  for dset in ${test_sets}; do

    inference_dir="${exp_dir}/exp/${model_dir}/${inference_checkpoint}/${dset}"
    inference_dir="${exp_dir}/exp/${model_dir}/inference-${inference_checkpoint}/${dset}"
    _logdir="${inference_dir}/logdir"
    echo "inference_dir: ${inference_dir}"

    mkdir -p "${_logdir}"
    data_dir="${feats_dir}/data/${dset}"
@@ -155,7 +156,7 @@
    done
    utils/split_scp.pl "${key_file}" ${split_scps}

    gpuid_list_array=(${gpuid_list//,/ })
    gpuid_list_array=(${CUDA_VISIBLE_DEVICES//,/ })
    for JOB in $(seq ${nj}); do
        {
          id=$((JOB-1))
@@ -171,6 +172,8 @@
          ++input="${_logdir}/keys.${JOB}.scp" \
          ++output_dir="${inference_dir}/${JOB}" \
          ++device="${inference_device}" \
          ++ncpu=1 \
          ++disable_log=true \
          ++batch_size="${inference_batch_size}" &> ${_logdir}/log.${JOB}.txt
        }&

@@ -187,8 +190,8 @@
    done

    echo "Computing WER ..."
    cp ${inference_dir}/1best_recog/text ${inference_dir}/1best_recog/text.proc
    cp ${data_dir}/text ${inference_dir}/1best_recog/text.ref
    python utils/postprocess_text_zh.py ${inference_dir}/1best_recog/text ${inference_dir}/1best_recog/text.proc
    python utils/postprocess_text_zh.py  ${data_dir}/text ${inference_dir}/1best_recog/text.ref
    python utils/compute_wer.py ${inference_dir}/1best_recog/text.ref ${inference_dir}/1best_recog/text.proc ${inference_dir}/1best_recog/text.cer
    tail -n 3 ${inference_dir}/1best_recog/text.cer
  done