Merge pull request #473 from alibaba-damo-academy/dev_smohan

jmwang66

2023-05-09 8dab6d184a034ca86eafa644ea0d2100aadfe27d

 egs/alimeeting/sa-asr/asr_local.sh

@@ -434,14 +434,14 @@
           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" ${_dirs}
        else
           log "Skip stage 2: Speed perturbation"
        fi
@@ -473,9 +473,11 @@
                        _suf=""
                    fi
                fi
                utils/copy_data_dir.sh --validate_opts --non-print data/"${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}/${dset}/{segments,wav.scp,reco2file_and_channel,reco2dur}
                _opts=
@@ -488,7 +490,7 @@
                    _opts+="--segments data/${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 +517,7 @@
        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 +566,15 @@
                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 +590,7 @@
        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 +608,7 @@
            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}/${dset}/oracle_embedding.scp)"
            # generate oracle_profile and cluster_profile from oracle_embedding and cluster_embedding (padding the speaker during training)
@@ -615,6 +621,7 @@
            fi
            # generate cluster_profile with spectral-cluster directly (for infering and without oracle information)
            if [ "${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
@@ -1283,6 +1290,7 @@
            ${_cmd} --gpu "${_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 ${njob_infer} \
@@ -1312,10 +1320,10 @@
            _data="${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 utils/proce_text.py ${_data}/text ${_data}/text.proc
            python utils/proce_text.py ${_dir}/text ${_dir}/text.proc

            python local/compute_wer.py ${_data}/text.proc ${_dir}/text.proc ${_dir}/text.cer
            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
            
@@ -1390,6 +1398,7 @@
            ${_cmd} --gpu "${_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 ${njob_infer} \
@@ -1421,10 +1430,10 @@
            _data="${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
            python utils/proce_text.py ${_data}/text ${_data}/text.proc
            python utils/proce_text.py ${_dir}/text ${_dir}/text.proc

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

@@ -1506,6 +1515,7 @@
            ${_cmd} --gpu "${_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 ${njob_infer} \
@@ -1536,10 +1546,10 @@
            _data="${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
            python utils/proce_text.py ${_data}/text ${_data}/text.proc
            python utils/proce_text.py ${_dir}/text ${_dir}/text.proc

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