aishell example

游雁

2024-02-19 4ebde3c4ac27c15ff39ffbd5aa601035d189497a

aishell example

 examples/aishell/paraformer/run.sh

@@ -39,23 +39,14 @@
valid_set=dev
test_sets="dev test"

asr_config=train_asr_paraformer_conformer_12e_6d_2048_256.yaml
model_dir="baseline_$(basename "${asr_config}" .yaml)_${lang}_${token_type}_${tag}"
config=train_asr_paraformer_conformer_12e_6d_2048_256.yaml
model_dir="baseline_$(basename "${config}" .yaml)_${lang}_${token_type}_${tag}"

#inference_config=conf/decode_asr_transformer_noctc_1best.yaml
#inference_asr_model=valid.acc.ave_10best.pb
inference_device="cuda" #"cpu"
inference_checkpoint="model.pt"
inference_scp="wav.scp"

## you can set gpu num for decoding here
#gpuid_list=$CUDA_VISIBLE_DEVICES  # set gpus for decoding, the same as training stage by default
#ngpu=$(echo $gpuid_list | awk -F "," '{print NF}')
#
#if ${gpu_inference}; then
#    inference_nj=$[${ngpu}*${njob}]
#    _ngpu=1
#else
#    inference_nj=$njob
#    _ngpu=0
#fi


if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
    echo "stage -1: Data Download"
@@ -85,10 +76,10 @@

if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
    echo "stage 1: Feature and CMVN Generation"
#    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
#    utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$config" --scale 1.0
    python ../../../funasr/bin/compute_audio_cmvn.py \
    --config-path "${workspace}" \
    --config-name "${asr_config}" \
    --config-name "${config}" \
    ++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
    ++cmvn_file="${feats_dir}/data/${train_set}/cmvn.json" \
    ++dataset_conf.num_workers=$nj
@@ -118,88 +109,82 @@
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
echo "stage 4: ASR Training"

  log_file="${exp_dir}/exp/${model_dir}/train.log.txt"
  echo "log_file: ${log_file}"
  torchrun \
  --nnodes 1 \
  --nproc_per_node ${gpu_num} \
  ../../../funasr/bin/train.py \
  --config-path "${workspace}" \
  --config-name "${asr_config}" \
  --config-name "${config}" \
  ++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
  ++cmvn_file="${feats_dir}/data/${train_set}/am.mvn" \
  ++token_list="${token_list}" \
  ++output_dir="${exp_dir}/exp/${model_dir}"
  ++tokenizer_conf.token_list="${token_list}" \
  ++frontend_conf.cmvn_file="${feats_dir}/data/${train_set}/am.mvn" \
  ++output_dir="${exp_dir}/exp/${model_dir}" &> ${log_file}
fi

#
## Testing Stage
#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 "${inference_config}" .yaml)"
#        _dir="${asr_exp}/${inference_tag}/${inference_asr_model}/${dset}"
#        _logdir="${_dir}/logdir"
#        if [ -d ${_dir} ]; then
#            echo "${_dir} is already exists. if you want to decode again, please delete this dir first."
#            exit 0
#        fi
#        mkdir -p "${_logdir}"
#        _data="${feats_dir}/data/${dset}"
#        key_file=${_data}/${scp}
#        num_scp_file="$(<${key_file} wc -l)"
#        _nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
#        split_scps=
#        for n in $(seq "${_nj}"); do
#            split_scps+=" ${_logdir}/keys.${n}.scp"
#        done
#        # shellcheck disable=SC2086
#        utils/split_scp.pl "${key_file}" ${split_scps}
#        _opts=
#        if [ -n "${inference_config}" ]; then
#            _opts+="--config ${inference_config} "
#        fi
#        ${infer_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
#            python -m funasr.bin.asr_inference_launch \
#                --batch_size 1 \
#                --ngpu "${_ngpu}" \
#                --njob ${njob} \
#                --gpuid_list ${gpuid_list} \
#                --data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
#                --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
#                --key_file "${_logdir}"/keys.JOB.scp \
#                --asr_train_config "${asr_exp}"/config.yaml \
#                --asr_model_file "${asr_exp}"/"${inference_asr_model}" \
#                --output_dir "${_logdir}"/output.JOB \
#                --mode paraformer \
#                ${_opts}
#
#        for f in token token_int score text; do
#            if [ -f "${_logdir}/output.1/1best_recog/${f}" ]; then
#                for i in $(seq "${_nj}"); do
#                    cat "${_logdir}/output.${i}/1best_recog/${f}"
#                done | sort -k1 >"${_dir}/${f}"
#            fi
#        done
#        python utils/proce_text.py ${_dir}/text ${_dir}/text.proc
#        python utils/proce_text.py ${_data}/text ${_data}/text.proc
#        python utils/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
#        tail -n 3 ${_dir}/text.cer > ${_dir}/text.cer.txt
#        cat ${_dir}/text.cer.txt
#    done
#fi
#
## Prepare files for ModelScope fine-tuning and inference
#if [ ${stage} -le 6 ] && [ ${stop_stage} -ge 6 ]; then
#    echo "stage 6: ModelScope Preparation"
#    cp ${feats_dir}/data/${train_set}/cmvn/am.mvn ${exp_dir}/exp/${model_dir}/am.mvn
#    vocab_size=$(cat ${token_list} | wc -l)
#    python utils/gen_modelscope_configuration.py \
#        --am_model_name $inference_asr_model \
#        --mode paraformer \
#        --model_name paraformer \
#        --dataset aishell \
#        --output_dir $exp_dir/exp/$model_dir \
#        --vocab_size $vocab_size \
#        --nat _nat \
#        --tag $tag
#fi


# Testing Stage
if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
  echo "stage 5: Inference"

  if ${inference_device} == "cuda"; then
      nj=$(echo CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
  else
      nj=$njob
      batch_size=1
      gpuid_list=""
      for JOB in $(seq ${nj}); do
          gpuid_list=CUDA_VISIBLE_DEVICES"-1,"
      done
  fi

  for dset in ${test_sets}; do

    inference_dir="${asr_exp}/${inference_checkpoint}/${dset}"
    _logdir="${inference_dir}/logdir"

    mkdir -p "${_logdir}"
    data_dir="${feats_dir}/data/${dset}"
    key_file=${data_dir}/${inference_scp}

    split_scps=
    for JOB in $(seq "${nj}"); do
        split_scps+=" ${_logdir}/keys.${JOB}.scp"
    done
    utils/split_scp.pl "${key_file}" ${split_scps}

    for JOB in $(seq ${nj}); do
        {
          python ../../../funasr/bin/inference.py \
          --config-path="${exp_dir}/exp/${model_dir}" \
          --config-name="config.yaml" \
          ++init_param="${exp_dir}/exp/${model_dir}/${inference_checkpoint}" \
          ++tokenizer_conf.token_list="${token_list}" \
          ++frontend_conf.cmvn_file="${feats_dir}/data/${train_set}/am.mvn" \
          ++input="${_logdir}/keys.${JOB}.scp" \
          ++output_dir="${inference_dir}/${JOB}" \
          ++device="${inference_device}"
        }&

    done
    wait

    mkdir -p ${inference_dir}/1best_recog
    for f in token score text; do
        if [ -f "${inference_dir}/${JOB}/1best_recog/${f}" ]; then
          for JOB in $(seq "${nj}"); do
              cat "${inference_dir}/${JOB}/1best_recog/${f}"
          done | sort -k1 >"${inference_dir}/1best_recog/${f}"
        fi
    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/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

fi

 examples/aishell/paraformer/utils/compute_wer.py

New file
@@ -0,0 +1,157 @@
import os
import numpy as np
import sys

def compute_wer(ref_file,
                hyp_file,
                cer_detail_file):
    rst = {
        'Wrd': 0,
        'Corr': 0,
        'Ins': 0,
        'Del': 0,
        'Sub': 0,
        'Snt': 0,
        'Err': 0.0,
        'S.Err': 0.0,
        'wrong_words': 0,
        'wrong_sentences': 0
    }

    hyp_dict = {}
    ref_dict = {}
    with open(hyp_file, 'r') as hyp_reader:
        for line in hyp_reader:
            key = line.strip().split()[0]
            value = line.strip().split()[1:]
            hyp_dict[key] = value
    with open(ref_file, 'r') as ref_reader:
        for line in ref_reader:
            key = line.strip().split()[0]
            value = line.strip().split()[1:]
            ref_dict[key] = value

    cer_detail_writer = open(cer_detail_file, 'w')
    for hyp_key in hyp_dict:
        if hyp_key in ref_dict:
           out_item = compute_wer_by_line(hyp_dict[hyp_key], ref_dict[hyp_key])
           rst['Wrd'] += out_item['nwords']
           rst['Corr'] += out_item['cor']
           rst['wrong_words'] += out_item['wrong']
           rst['Ins'] += out_item['ins']
           rst['Del'] += out_item['del']
           rst['Sub'] += out_item['sub']
           rst['Snt'] += 1
           if out_item['wrong'] > 0:
               rst['wrong_sentences'] += 1
           cer_detail_writer.write(hyp_key + print_cer_detail(out_item) + '\n')
           cer_detail_writer.write("ref:" + '\t' + " ".join(list(map(lambda x: x.lower(), ref_dict[hyp_key]))) + '\n')
           cer_detail_writer.write("hyp:" + '\t' + " ".join(list(map(lambda x: x.lower(), hyp_dict[hyp_key]))) + '\n')

    if rst['Wrd'] > 0:
        rst['Err'] = round(rst['wrong_words'] * 100 / rst['Wrd'], 2)
    if rst['Snt'] > 0:
        rst['S.Err'] = round(rst['wrong_sentences'] * 100 / rst['Snt'], 2)

    cer_detail_writer.write('\n')
    cer_detail_writer.write("%WER " + str(rst['Err']) + " [ " + str(rst['wrong_words'])+ " / " + str(rst['Wrd']) +
                            ", " + str(rst['Ins']) + " ins, " + str(rst['Del']) + " del, " + str(rst['Sub']) + " sub ]" + '\n')
    cer_detail_writer.write("%SER " + str(rst['S.Err']) + " [ " + str(rst['wrong_sentences']) + " / " + str(rst['Snt']) + " ]" + '\n')
    cer_detail_writer.write("Scored " + str(len(hyp_dict)) + " sentences, " + str(len(hyp_dict) - rst['Snt']) + " not present in hyp." + '\n')

     
def compute_wer_by_line(hyp,
                        ref):
    hyp = list(map(lambda x: x.lower(), hyp))
    ref = list(map(lambda x: x.lower(), ref))

    len_hyp = len(hyp)
    len_ref = len(ref)

    cost_matrix = np.zeros((len_hyp + 1, len_ref + 1), dtype=np.int16)

    ops_matrix = np.zeros((len_hyp + 1, len_ref + 1), dtype=np.int8)

    for i in range(len_hyp + 1):
        cost_matrix[i][0] = i
    for j in range(len_ref + 1):
        cost_matrix[0][j] = j

    for i in range(1, len_hyp + 1):
        for j in range(1, len_ref + 1):
            if hyp[i - 1] == ref[j - 1]:
                cost_matrix[i][j] = cost_matrix[i - 1][j - 1]
            else:
                substitution = cost_matrix[i - 1][j - 1] + 1
                insertion = cost_matrix[i - 1][j] + 1
                deletion = cost_matrix[i][j - 1] + 1

                compare_val = [substitution, insertion, deletion]

                min_val = min(compare_val)
                operation_idx = compare_val.index(min_val) + 1
                cost_matrix[i][j] = min_val
                ops_matrix[i][j] = operation_idx

    match_idx = []
    i = len_hyp
    j = len_ref
    rst = {
        'nwords': len_ref,
        'cor': 0,
        'wrong': 0,
        'ins': 0,
        'del': 0,
        'sub': 0
    }
    while i >= 0 or j >= 0:
        i_idx = max(0, i)
        j_idx = max(0, j)

        if ops_matrix[i_idx][j_idx] == 0:  # correct
            if i - 1 >= 0 and j - 1 >= 0:
                match_idx.append((j - 1, i - 1))
                rst['cor'] += 1

            i -= 1
            j -= 1

        elif ops_matrix[i_idx][j_idx] == 2:  # insert
            i -= 1
            rst['ins'] += 1

        elif ops_matrix[i_idx][j_idx] == 3:  # delete
            j -= 1
            rst['del'] += 1

        elif ops_matrix[i_idx][j_idx] == 1:  # substitute
            i -= 1
            j -= 1
            rst['sub'] += 1

        if i < 0 and j >= 0:
            rst['del'] += 1
        elif j < 0 and i >= 0:
            rst['ins'] += 1

    match_idx.reverse()
    wrong_cnt = cost_matrix[len_hyp][len_ref]
    rst['wrong'] = wrong_cnt

    return rst

def print_cer_detail(rst):
    return ("(" + "nwords=" + str(rst['nwords']) + ",cor=" + str(rst['cor'])
            + ",ins=" + str(rst['ins']) + ",del=" + str(rst['del']) + ",sub="
            + str(rst['sub']) + ") corr:" + '{:.2%}'.format(rst['cor']/rst['nwords'])
            + ",cer:" + '{:.2%}'.format(rst['wrong']/rst['nwords']))

if __name__ == '__main__':
    if len(sys.argv) != 4:
        print("usage : python compute-wer.py test.ref test.hyp test.wer")
        sys.exit(0)

    ref_file = sys.argv[1]
    hyp_file = sys.argv[2]
    cer_detail_file = sys.argv[3]
    compute_wer(ref_file, hyp_file, cer_detail_file)

 examples/industrial_data_pretraining/paraformer/finetune.sh

@@ -6,10 +6,10 @@
#git clone https://www.modelscope.cn/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}

## generate jsonl from wav.scp and text.txt
python funasr/datasets/audio_datasets/scp2jsonl.py \
++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
++data_type_list='["source", "target"]' \
++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
#python funasr/datasets/audio_datasets/scp2jsonl.py \
#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
#++data_type_list='["source", "target"]' \
#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl


# torchrun \
@@ -24,5 +24,4 @@
++dataset_conf.batch_type="example" \
++train_conf.max_epoch=2 \
++dataset_conf.num_workers=4 \
+output_dir="outputs/debug/ckpt/funasr2/exp2" \
+debug="true"
+output_dir="outputs/debug/ckpt/funasr2/exp2"

 examples/industrial_data_pretraining/paraformer/infer_demo.sh

File was renamed from examples/industrial_data_pretraining/paraformer/infer.sh
@@ -9,3 +9,6 @@
+output_dir="./outputs/debug" \
+device="cpu" \