Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into ...

雾聪

2023-05-17 8706e767affc6bdc8cb7a67ca3a20a62779ff048

 egs/alimeeting/sa-asr/asr_local.sh

@@ -107,8 +107,8 @@
                                      # inference_asr_model=valid.acc.best.pth
                                      # inference_asr_model=valid.loss.ave.pth
inference_sa_asr_model=valid.acc_spk.ave.pb
download_model= # Download a model from Model Zoo and use it for decoding.

infer_with_pretrained_model=false   # Use pretrained model for decoding
download_sa_asr_model=          # Download the SA-ASR model from ModelScope and use it for decoding.
# [Task dependent] Set the datadir name created by local/data.sh
train_set=       # Name of training set.
valid_set=       # Name of validation set used for monitoring/tuning network training.
@@ -203,7 +203,8 @@
                          # Note that it will overwrite args in inference config.
    --inference_lm        # Language modle path for decoding (default="${inference_lm}").
    --inference_asr_model # ASR model path for decoding (default="${inference_asr_model}").
    --download_model      # Download a model from Model Zoo and use it for decoding (default="${download_model}").
    --infer_with_pretrained_model      # Use pretrained model for decoding (default="${infer_with_pretrained_model}").
    --download_sa_asr_model=          # Download the SA-ASR model from ModelScope and use it for decoding(default="${download_sa_asr_model}").

    # [Task dependent] Set the datadir name created by local/data.sh
    --train_set     # Name of training set (required).
@@ -304,6 +305,9 @@
    lm_token_type="${token_type}"
fi

if ${infer_with_pretrained_model}; then
    skip_train=true
fi

# Set tag for naming of model directory
if [ -z "${asr_tag}" ]; then
@@ -434,14 +438,14 @@
           log "Stage 2: Speed perturbation: data/${train_set} -> data/${train_set}_sp"
           for factor in ${speed_perturb_factors}; do
               if [[ $(bc <<<"${factor} != 1.0") == 1 ]]; then
                   scripts/utils/perturb_data_dir_speed.sh "${factor}" "data/${train_set}" "data/${train_set}_sp${factor}"
                   local/perturb_data_dir_speed.sh "${factor}" "data/${train_set}" "data/${train_set}_sp${factor}"
                   _dirs+="data/${train_set}_sp${factor} "
               else
                   # If speed factor is 1, same as the original
                   _dirs+="data/${train_set} "
               fi
           done
           utils/combine_data.sh "data/${train_set}_sp" ${_dirs}
           local/combine_data.sh "data/${train_set}_sp" ${_dirs}
        else
           log "Skip stage 2: Speed perturbation"
        fi
@@ -473,9 +477,11 @@
                        _suf=""
                    fi
                fi
                utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"
                local/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"
                
                cp data/"${dset}"/utt2spk_all_fifo "${data_feats}${_suf}/${dset}/"
                if [ "${dset}" = "Train_Ali_far" ] || [ "${dset}" = "Eval_Ali_far" ] || [ "${dset}" = "Test_Ali_far" ]; then
                    cp data/"${dset}"/utt2spk_all_fifo "${data_feats}${_suf}/${dset}/"
                fi

                rm -f ${data_feats}${_suf}/${dset}/{segments,wav.scp,reco2file_and_channel,reco2dur}
                _opts=
@@ -488,7 +494,7 @@
                    _opts+="--segments data/${dset}/segments "
                fi
                # shellcheck disable=SC2086
                scripts/audio/format_wav_scp.sh --nj "${nj}" --cmd "${train_cmd}" \
                local/format_wav_scp.sh --nj "${nj}" --cmd "${train_cmd}" \
                    --audio-format "${audio_format}" --fs "${fs}" ${_opts} \
                    "data/${dset}/wav.scp" "${data_feats}${_suf}/${dset}"

@@ -515,7 +521,7 @@
        for dset in $rm_dset; do

            # Copy data dir
            utils/copy_data_dir.sh --validate_opts --non-print "${data_feats}/org/${dset}" "${data_feats}/${dset}"
            local/copy_data_dir.sh --validate_opts --non-print "${data_feats}/org/${dset}" "${data_feats}/${dset}"
            cp "${data_feats}/org/${dset}/feats_type" "${data_feats}/${dset}/feats_type"

            # Remove short utterances
@@ -564,12 +570,15 @@
                awk ' { if( NF != 1 ) print $0; } ' >"${data_feats}/${dset}/text"

            # fix_data_dir.sh leaves only utts which exist in all files
            utils/fix_data_dir.sh "${data_feats}/${dset}"
            local/fix_data_dir.sh "${data_feats}/${dset}"

            # generate uttid
            cut -d ' ' -f 1 "${data_feats}/${dset}/wav.scp" > "${data_feats}/${dset}/uttid"
            # filter utt2spk_all_fifo
            python local/filter_utt2spk_all_fifo.py ${data_feats}/${dset}/uttid ${data_feats}/org/${dset} ${data_feats}/${dset}
            
            if [ "${dset}" = "Train_Ali_far" ] || [ "${dset}" = "Eval_Ali_far" ] || [ "${dset}" = "Test_Ali_far" ]; then
                # filter utt2spk_all_fifo
                python local/filter_utt2spk_all_fifo.py ${data_feats}/${dset}/uttid ${data_feats}/org/${dset} ${data_feats}/${dset}
            fi
        done

        # shellcheck disable=SC2002
@@ -585,7 +594,7 @@
        echo "<blank>" > ${token_list}
        echo "<s>" >> ${token_list}
        echo "</s>" >> ${token_list}
        local/text2token.py -s 1 -n 1 --space "" ${data_feats}/lm_train.txt | cut -f 2- -d" " | tr " " "\n" \
        utils/text2token.py -s 1 -n 1 --space "" ${data_feats}/lm_train.txt | cut -f 2- -d" " | tr " " "\n" \
            | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
        num_token=$(cat ${token_list} | wc -l)
        echo "<unk>" >> ${token_list}
@@ -603,6 +612,7 @@
            python local/process_text_id.py ${data_feats}/${dset}
            log "Successfully generate ${data_feats}/${dset}/text_id_train"
            # generate oracle_embedding from single-speaker audio segment
            log "oracle_embedding is being generated in the background, and the log is profile_log/gen_oracle_embedding_${dset}.log"
            python local/gen_oracle_embedding.py "${data_feats}/${dset}" "data/local/${dset}_correct_single_speaker" &> "profile_log/gen_oracle_embedding_${dset}.log"
            log "Successfully generate oracle embedding for ${dset} (${data_feats}/${dset}/oracle_embedding.scp)"
            # generate oracle_profile and cluster_profile from oracle_embedding and cluster_embedding (padding the speaker during training)
@@ -615,6 +625,7 @@
            fi
            # generate cluster_profile with spectral-cluster directly (for infering and without oracle information)
            if [ "${dset}" = "${valid_set}" ] || [ "${dset}" = "${test_sets}" ]; then
                log "cluster_profile is being generated in the background, and the log is profile_log/gen_cluster_profile_infer_${dset}.log"
                python local/gen_cluster_profile_infer.py "${data_feats}/${dset}" "data/local/${dset}" 0.996 0.815 &> "profile_log/gen_cluster_profile_infer_${dset}.log"
                log "Successfully generate cluster profile for ${dset} (${data_feats}/${dset}/cluster_profile_infer.scp)"
            fi
@@ -1213,118 +1224,20 @@
    log "Skip the training stages"
fi

if ${infer_with_pretrained_model}; then
    log "Use ${download_sa_asr_model} for decoding and evaluation"
    sa_asr_exp="${expdir}/${download_sa_asr_model}"
    mkdir -p "${sa_asr_exp}"


    python local/download_pretrained_model_from_modelscope.py $download_sa_asr_model ${expdir}
    inference_sa_asr_model="model.pb"
    inference_config=${sa_asr_exp}/decoding.yaml
fi

if ! "${skip_eval}"; then
    if [ ${stage} -le 13 ] && [ ${stop_stage} -ge 13 ]; then
        log "Stage 13: Decoding multi-talker ASR: training_dir=${asr_exp}"

        if ${gpu_inference}; then
            _cmd="${cuda_cmd}"
            inference_nj=$[${ngpu}*${njob_infer}]
            _ngpu=1

        else
            _cmd="${decode_cmd}"
            inference_nj=$inference_nj
            _ngpu=0
        fi

        _opts=
        if [ -n "${inference_config}" ]; then
            _opts+="--config ${inference_config} "
        fi
        if "${use_lm}"; then
            if "${use_word_lm}"; then
                _opts+="--word_lm_train_config ${lm_exp}/config.yaml "
                _opts+="--word_lm_file ${lm_exp}/${inference_lm} "
            else
                _opts+="--lm_train_config ${lm_exp}/config.yaml "
                _opts+="--lm_file ${lm_exp}/${inference_lm} "
            fi
        fi

        # 2. Generate run.sh
        log "Generate '${asr_exp}/${inference_tag}/run.sh'. You can resume the process from stage 13 using this script"
        mkdir -p "${asr_exp}/${inference_tag}"; echo "${run_args} --stage 13 \"\$@\"; exit \$?" > "${asr_exp}/${inference_tag}/run.sh"; chmod +x "${asr_exp}/${inference_tag}/run.sh"

        for dset in ${test_sets}; do
            _data="${data_feats}/${dset}"
            _dir="${asr_exp}/${inference_tag}/${dset}"
            _logdir="${_dir}/logdir"
            mkdir -p "${_logdir}"

            _feats_type="$(<${_data}/feats_type)"
            if [ "${_feats_type}" = raw ]; then
                _scp=wav.scp
                if [[ "${audio_format}" == *ark* ]]; then
                    _type=kaldi_ark
                else
                    _type=sound
                fi
            else
                _scp=feats.scp
                _type=kaldi_ark
            fi

            # 1. Split the key file
            key_file=${_data}/${_scp}
            split_scps=""
            _nj=$(min "${inference_nj}" "$(<${key_file} wc -l)")
            echo $_nj
            for n in $(seq "${_nj}"); do
                split_scps+=" ${_logdir}/keys.${n}.scp"
            done
            # shellcheck disable=SC2086
            utils/split_scp.pl "${key_file}" ${split_scps}

            # 2. Submit decoding jobs
            log "Decoding started... log: '${_logdir}/asr_inference.*.log'"
            
            ${_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
                python -m funasr.bin.asr_inference_launch \
                    --batch_size 1 \
                    --nbest 1   \
                    --ngpu "${_ngpu}" \
                    --njob ${njob_infer} \
                    --gpuid_list ${device} \
                    --data_path_and_name_and_type "${_data}/${_scp},speech,${_type}" \
                    --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 asr \
                    ${_opts}

            # 3. Concatenates the output files from each jobs
            for f in token token_int score text; do
                for i in $(seq "${_nj}"); do
                    cat "${_logdir}/output.${i}/1best_recog/${f}"
                done | LC_ALL=C sort -k1 >"${_dir}/${f}"
            done
        done
    fi


    if [ ${stage} -le 14 ] && [ ${stop_stage} -ge 14 ]; then
        log "Stage 14: Scoring multi-talker ASR"

        for dset in ${test_sets}; do
            _data="${data_feats}/${dset}"
            _dir="${asr_exp}/${inference_tag}/${dset}"

            python local/proce_text.py ${_data}/text ${_data}/text.proc
            python local/proce_text.py ${_dir}/text ${_dir}/text.proc

            python local/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

    if [ ${stage} -le 15 ] && [ ${stop_stage} -ge 15 ]; then
        log "Stage 15: Decoding SA-ASR (oracle profile): training_dir=${sa_asr_exp}"
        log "Stage 13: Decoding SA-ASR (oracle profile): training_dir=${sa_asr_exp}"

        if ${gpu_inference}; then
            _cmd="${cuda_cmd}"
@@ -1390,6 +1303,7 @@
            ${_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
                python -m funasr.bin.asr_inference_launch \
                    --batch_size 1 \
                    --mc True   \
                    --nbest 1   \
                    --ngpu "${_ngpu}" \
                    --njob ${njob_infer} \
@@ -1414,17 +1328,20 @@
        done
    fi

    if [ ${stage} -le 16 ] && [ ${stop_stage} -ge 16 ]; then
        log "Stage 16: Scoring SA-ASR (oracle profile)"
    if [ ${stage} -le 14 ] && [ ${stop_stage} -ge 14 ]; then
        log "Stage 14: Scoring SA-ASR (oracle profile)"

        for dset in ${test_sets}; do
            _data="${data_feats}/${dset}"
            _dir="${sa_asr_exp}/${sa_asr_inference_tag}.oracle/${dset}"

            python local/proce_text.py ${_data}/text ${_data}/text.proc
            python local/proce_text.py ${_dir}/text ${_dir}/text.proc
            sed 's/\$//g' ${_data}/text > ${_data}/text_nosrc
            sed 's/\$//g' ${_dir}/text > ${_dir}/text_nosrc

            python local/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
            python utils/proce_text.py ${_data}/text_nosrc ${_data}/text.proc
            python utils/proce_text.py ${_dir}/text_nosrc ${_dir}/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

@@ -1439,8 +1356,8 @@

    fi

    if [ ${stage} -le 17 ] && [ ${stop_stage} -ge 17 ]; then
        log "Stage 17: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"
    if [ ${stage} -le 15 ] && [ ${stop_stage} -ge 15 ]; then
        log "Stage 15: Decoding SA-ASR (cluster profile): training_dir=${sa_asr_exp}"

        if ${gpu_inference}; then
            _cmd="${cuda_cmd}"
@@ -1506,6 +1423,7 @@
            ${_cmd} --gpu "${_ngpu}" --max-jobs-run "${_nj}" JOB=1:"${_nj}" "${_logdir}"/asr_inference.JOB.log \
                python -m funasr.bin.asr_inference_launch \
                    --batch_size 1 \
                    --mc True   \
                    --nbest 1   \
                    --ngpu "${_ngpu}" \
                    --njob ${njob_infer} \
@@ -1529,17 +1447,20 @@
        done
    fi

    if [ ${stage} -le 18 ] && [ ${stop_stage} -ge 18 ]; then
        log "Stage 18: Scoring SA-ASR (cluster profile)"
    if [ ${stage} -le 16 ] && [ ${stop_stage} -ge 16 ]; then
        log "Stage 16: Scoring SA-ASR (cluster profile)"

        for dset in ${test_sets}; do
            _data="${data_feats}/${dset}"
            _dir="${sa_asr_exp}/${sa_asr_inference_tag}.cluster/${dset}"

            python local/proce_text.py ${_data}/text ${_data}/text.proc
            python local/proce_text.py ${_dir}/text ${_dir}/text.proc
            sed 's/\$//g' ${_data}/text > ${_data}/text_nosrc
            sed 's/\$//g' ${_dir}/text > ${_dir}/text_nosrc

            python local/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
            python utils/proce_text.py ${_data}/text_nosrc ${_data}/text.proc
            python utils/proce_text.py ${_dir}/text_nosrc ${_dir}/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