update

.github/workflows/main.yml

@@ -1,43 +0,0 @@
-name: "FunASR Docs"
-on:
-  pull_request:
-    branches:
-      - main
-  push:
-    branches:
-      - main
-      - dev_lyh
-
-jobs:
-  docs:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v1
-      - uses: ammaraskar/sphinx-action@master
-        with:
-          docs-folder: "docs/"
-          pre-build-command: "pip install sphinx-markdown-tables nbsphinx jinja2 recommonmark sphinx_rtd_theme"
-      - uses: ammaraskar/sphinx-action@master
-        with:
-          docs-folder: "docs/m2met2/"
-          pre-build-command: "pip install sphinx-markdown-tables nbsphinx jinja2 recommonmark sphinx_rtd_theme myst-parser"
-
-      - name: deploy copy
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh' || github.ref == 'refs/heads/dev_lhn'
-        run: |
-          mkdir public
-          touch public/.nojekyll
-          mkdir public/en
-          touch public/en/.nojekyll
-          cp -r docs/_build/html/* public/en/
-          mkdir public/m2met2
-          touch public/m2met2/.nojekyll
-          cp -r docs/m2met2/_build/html/* public/m2met2/
-
-      - name: deploy github.io pages
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev_wjm' || github.ref == 'refs/heads/dev_lyh' || github.ref == 'refs/heads/dev_lhn'
-        uses: peaceiris/actions-gh-pages@v2.3.1
-        env:
-          GITHUB_TOKEN: ${{ secrets.ACCESS_TOKEN }}
-          PUBLISH_BRANCH: gh-pages
-          PUBLISH_DIR: public

examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml

@@ -0,0 +1,116 @@
+# This is an example that demonstrates how to configure a model file.
+# You can modify the configuration according to your own requirements.
+
+# to print the register_table:
+# from funasr.register import tables
+# tables.print()
+
+# network architecture
+model: Conformer
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1     # label smoothing option
+    length_normalized_loss: false
+
+# encoder
+encoder: ConformerEncoder
+encoder_conf:
+    output_size: 256    # dimension of attention
+    attention_heads: 4
+    linear_units: 2048  # the number of units of position-wise feed forward
+    num_blocks: 12      # the number of encoder blocks
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d # encoder architecture type
+    normalize_before: true
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    macaron_style: true
+    use_cnn_module: true
+    cnn_module_kernel: 15
+
+# decoder
+decoder: TransformerDecoder
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.0
+    src_attention_dropout_rate: 0.0
+
+
+# frontend related
+frontend: WavFrontend
+frontend_conf:
+    fs: 16000
+    window: hamming
+    n_mels: 80
+    frame_length: 25
+    frame_shift: 10
+    lfr_m: 1
+    lfr_n: 1
+
+specaug: SpecAug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+
+train_conf:
+  accum_grad: 1
+  grad_clip: 5
+  max_epoch: 150
+  val_scheduler_criterion:
+      - valid
+      - acc
+  best_model_criterion:
+  -   - valid
+      - acc
+      - max
+  keep_nbest_models: 10
+  log_interval: 50
+
+optim: adam
+optim_conf:
+   lr: 0.0005
+scheduler: warmuplr
+scheduler_conf:
+   warmup_steps: 30000
+
+dataset: AudioDataset
+dataset_conf:
+    index_ds: IndexDSJsonl
+    batch_sampler: DynamicBatchLocalShuffleSampler
+    batch_type: example # example or length
+    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+    max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
+    buffer_size: 500
+    shuffle: True
+    num_workers: 4
+
+tokenizer: CharTokenizer
+tokenizer_conf:
+  unk_symbol: <unk>
+  split_with_space: true
+
+
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+normalize: null

examples/aishell/conformer/local/aishell_data_prep.sh

@@ -0,0 +1,66 @@
+#!/bin/bash
+
+# Copyright 2017 Xingyu Na
+# Apache 2.0
+
+#. ./path.sh || exit 1;
+
+if [ $# != 3 ]; then
+  echo "Usage: $0 <audio-path> <text-path> <output-path>"
+  echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data"
+  exit 1;
+fi
+
+aishell_audio_dir=$1
+aishell_text=$2/aishell_transcript_v0.8.txt
+output_dir=$3
+
+train_dir=$output_dir/data/local/train
+dev_dir=$output_dir/data/local/dev
+test_dir=$output_dir/data/local/test
+tmp_dir=$output_dir/data/local/tmp
+
+mkdir -p $train_dir
+mkdir -p $dev_dir
+mkdir -p $test_dir
+mkdir -p $tmp_dir
+
+# data directory check
+if [ ! -d $aishell_audio_dir ] || [ ! -f $aishell_text ]; then
+  echo "Error: $0 requires two directory arguments"
+  exit 1;
+fi
+
+# find wav audio file for train, dev and test resp.
+find $aishell_audio_dir -iname "*.wav" > $tmp_dir/wav.flist
+n=`cat $tmp_dir/wav.flist | wc -l`
+[ $n -ne 141925 ] && \
+  echo Warning: expected 141925 data data files, found $n
+
+grep -i "wav/train" $tmp_dir/wav.flist > $train_dir/wav.flist || exit 1;
+grep -i "wav/dev" $tmp_dir/wav.flist > $dev_dir/wav.flist || exit 1;
+grep -i "wav/test" $tmp_dir/wav.flist > $test_dir/wav.flist || exit 1;
+
+rm -r $tmp_dir
+
+# Transcriptions preparation
+for dir in $train_dir $dev_dir $test_dir; do
+  echo Preparing $dir transcriptions
+  sed -e 's/\.wav//' $dir/wav.flist | awk -F '/' '{print $NF}' > $dir/utt.list
+  paste -d' ' $dir/utt.list $dir/wav.flist > $dir/wav.scp_all
+  utils/filter_scp.pl -f 1 $dir/utt.list $aishell_text > $dir/transcripts.txt
+  awk '{print $1}' $dir/transcripts.txt > $dir/utt.list
+  utils/filter_scp.pl -f 1 $dir/utt.list $dir/wav.scp_all | sort -u > $dir/wav.scp
+  sort -u $dir/transcripts.txt > $dir/text
+done
+
+mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test
+
+for f in wav.scp text; do
+  cp $train_dir/$f $output_dir/data/train/$f || exit 1;
+  cp $dev_dir/$f $output_dir/data/dev/$f || exit 1;
+  cp $test_dir/$f $output_dir/data/test/$f || exit 1;
+done
+
+echo "$0: AISHELL data preparation succeeded"
+exit 0;

examples/aishell/conformer/local/download_and_untar.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+
+# Copyright   2014  Johns Hopkins University (author: Daniel Povey)
+#             2017  Xingyu Na
+# Apache 2.0
+
+remove_archive=false
+
+if [ "$1" == --remove-archive ]; then
+  remove_archive=true
+  shift
+fi
+
+if [ $# -ne 3 ]; then
+  echo "Usage: $0 [--remove-archive] <data-base> <url-base> <corpus-part>"
+  echo "e.g.: $0 /export/a05/xna/data www.openslr.org/resources/33 data_aishell"
+  echo "With --remove-archive it will remove the archive after successfully un-tarring it."
+  echo "<corpus-part> can be one of: data_aishell, resource_aishell."
+fi
+
+data=$1
+url=$2
+part=$3
+
+if [ ! -d "$data" ]; then
+  echo "$0: no such directory $data"
+  exit 1;
+fi
+
+part_ok=false
+list="data_aishell resource_aishell"
+for x in $list; do
+  if [ "$part" == $x ]; then part_ok=true; fi
+done
+if ! $part_ok; then
+  echo "$0: expected <corpus-part> to be one of $list, but got '$part'"
+  exit 1;
+fi
+
+if [ -z "$url" ]; then
+  echo "$0: empty URL base."
+  exit 1;
+fi
+
+if [ -f $data/$part/.complete ]; then
+  echo "$0: data part $part was already successfully extracted, nothing to do."
+  exit 0;
+fi
+
+# sizes of the archive files in bytes.
+sizes="15582913665 1246920"
+
+if [ -f $data/$part.tgz ]; then
+  size=$(/bin/ls -l $data/$part.tgz | awk '{print $5}')
+  size_ok=false
+  for s in $sizes; do if [ $s == $size ]; then size_ok=true; fi; done
+  if ! $size_ok; then
+    echo "$0: removing existing file $data/$part.tgz because its size in bytes $size"
+    echo "does not equal the size of one of the archives."
+    rm $data/$part.tgz
+  else
+    echo "$data/$part.tgz exists and appears to be complete."
+  fi
+fi
+
+if [ ! -f $data/$part.tgz ]; then
+  if ! command -v wget >/dev/null; then
+    echo "$0: wget is not installed."
+    exit 1;
+  fi
+  full_url=$url/$part.tgz
+  echo "$0: downloading data from $full_url.  This may take some time, please be patient."
+
+  cd $data || exit 1
+  if ! wget --no-check-certificate $full_url; then
+    echo "$0: error executing wget $full_url"
+    exit 1;
+  fi
+fi
+
+cd $data || exit 1
+
+if ! tar -xvzf $part.tgz; then
+  echo "$0: error un-tarring archive $data/$part.tgz"
+  exit 1;
+fi
+
+touch $data/$part/.complete
+
+if [ $part == "data_aishell" ]; then
+  cd $data/$part/wav || exit 1
+  for wav in ./*.tar.gz; do
+    echo "Extracting wav from $wav"
+    tar -zxf $wav && rm $wav
+  done
+fi
+
+echo "$0: Successfully downloaded and un-tarred $data/$part.tgz"
+
+if $remove_archive; then
+  echo "$0: removing $data/$part.tgz file since --remove-archive option was supplied."
+  rm $data/$part.tgz
+fi
+
+exit 0;

examples/aishell/conformer/run.sh

@@ -0,0 +1,194 @@
+#!/usr/bin/env bash
+
+
+CUDA_VISIBLE_DEVICES="0,1"
+
+# general configuration
+feats_dir="../DATA" #feature output dictionary
+exp_dir="."
+lang=zh
+token_type=char
+stage=0
+stop_stage=5
+
+# feature configuration
+nj=32
+
+inference_device="cuda" #"cpu"
+inference_checkpoint="model.pt"
+inference_scp="wav.scp"
+inference_batch_size=32
+
+# data
+raw_data=../raw_data
+data_url=www.openslr.org/resources/33
+
+# exp tag
+tag="exp1"
+workspace=`pwd`
+
+. utils/parse_options.sh || exit 1;
+
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+train_set=train
+valid_set=dev
+test_sets="dev test"
+
+config=conformer_12e_6d_2048_256.yaml
+model_dir="baseline_$(basename "${config}" .yaml)_${lang}_${token_type}_${tag}"
+
+
+if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
+    echo "stage -1: Data Download"
+    mkdir -p ${raw_data}
+    local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
+    local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
+fi
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    echo "stage 0: Data preparation"
+    # Data preparation
+    local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
+    for x in train dev test; do
+        cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
+        paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
+            > ${feats_dir}/data/${x}/text
+        utils/text2token.py -n 1 -s 1 ${feats_dir}/data/${x}/text > ${feats_dir}/data/${x}/text.org
+        mv ${feats_dir}/data/${x}/text.org ${feats_dir}/data/${x}/text
+
+        # convert wav.scp text to jsonl
+        scp_file_list_arg="++scp_file_list='[\"${feats_dir}/data/${x}/wav.scp\",\"${feats_dir}/data/${x}/text\"]'"
+        python ../../../funasr/datasets/audio_datasets/scp2jsonl.py \
+        ++data_type_list='["source", "target"]' \
+        ++jsonl_file_out=${feats_dir}/data/${x}/audio_datasets.jsonl \
+        ${scp_file_list_arg}
+    done
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    echo "stage 1: Feature and CMVN Generation"
+    python ../../../funasr/bin/compute_audio_cmvn.py \
+    --config-path "${workspace}/conf" \
+    --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
+fi
+
+token_list=${feats_dir}/data/${lang}_token_list/$token_type/tokens.txt
+echo "dictionary: ${token_list}"
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    echo "stage 2: Dictionary Preparation"
+    mkdir -p ${feats_dir}/data/${lang}_token_list/$token_type/
+   
+    echo "make a dictionary"
+    echo "<blank>" > ${token_list}
+    echo "<s>" >> ${token_list}
+    echo "</s>" >> ${token_list}
+    utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
+        | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
+    echo "<unk>" >> ${token_list}
+fi
+
+# LM Training Stage
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+  echo "stage 4: ASR Training"
+
+  mkdir -p ${exp_dir}/exp/${model_dir}
+  log_file="${exp_dir}/exp/${model_dir}/train.log.txt"
+  echo "log_file: ${log_file}"
+
+  gpu_num=$(echo CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+  torchrun \
+  --nnodes 1 \
+  --nproc_per_node ${gpu_num} \
+  ../../../funasr/bin/train.py \
+  --config-path "${workspace}/conf" \
+  --config-name "${config}" \
+  ++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
+  ++valid_data_set_list="${feats_dir}/data/${valid_set}/audio_datasets.jsonl" \
+  ++tokenizer_conf.token_list="${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"
+
+  if ${inference_device} == "cuda"; then
+      nj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+  else
+      inference_batch_size=1
+      CUDA_VISIBLE_DEVICES=""
+      for JOB in $(seq ${nj}); do
+          CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"-1,"
+      done
+  fi
+
+  for dset in ${test_sets}; do
+
+    inference_dir="${exp_dir}/exp/${model_dir}/${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}" ${split_scps}
+
+    gpuid_list_array=(${gpuid_list//,/ })
+    for JOB in $(seq ${nj}); do
+        {
+          id=$((JOB-1))
+          gpuid=${gpuid_list_array[$id]}
+
+          export CUDA_VISIBLE_DEVICES=${gpuid}
+          python ../../../funasr/bin/inference.py \
+          --config-path="${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}" \
+          ++batch_size="${inference_batch_size}"
+        }&
+
+    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/conformer/utils

@@ -0,0 +1 @@
+../paraformer/utils

examples/aishell/paraformer/run.sh

@@ -1,7 +1,6 @@
 #!/usr/bin/env bash
 
 
-
 CUDA_VISIBLE_DEVICES="0,1"
 
 # general configuration
@@ -18,6 +17,7 @@ nj=32
 inference_device="cuda" #"cpu"
 inference_checkpoint="model.pt"
 inference_scp="wav.scp"
+inference_batch_size=32
 
 # data
 raw_data=../raw_data
@@ -39,7 +39,7 @@ train_set=train
 valid_set=dev
 test_sets="dev test"
 
-config=train_asr_paraformer_conformer_12e_6d_2048_256.yaml
+config=paraformer_conformer_12e_6d_2048_256.yaml
 model_dir="baseline_$(basename "${config}" .yaml)_${lang}_${token_type}_${tag}"
 
 
@@ -129,19 +129,18 @@ 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}')
+      nj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
   else
-      nj=$njob
-      batch_size=1
-      gpuid_list=""
+      inference_batch_size=1
+      CUDA_VISIBLE_DEVICES=""
       for JOB in $(seq ${nj}); do
-          gpuid_list=CUDA_VISIBLE_DEVICES"-1,"
+          CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"-1,"
       done
   fi
 
   for dset in ${test_sets}; do
 
-    inference_dir="${asr_exp}/${inference_checkpoint}/${dset}"
+    inference_dir="${exp_dir}/exp/${model_dir}/${inference_checkpoint}/${dset}"
     _logdir="${inference_dir}/logdir"
 
     mkdir -p "${_logdir}"
@@ -154,8 +153,13 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
     done
     utils/split_scp.pl "${key_file}" ${split_scps}
 
+    gpuid_list_array=(${gpuid_list//,/ })
     for JOB in $(seq ${nj}); do
         {
+          id=$((JOB-1))
+          gpuid=${gpuid_list_array[$id]}
+
+          export CUDA_VISIBLE_DEVICES=${gpuid}
           python ../../../funasr/bin/inference.py \
           --config-path="${exp_dir}/exp/${model_dir}" \
           --config-name="config.yaml" \
@@ -164,7 +168,8 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
           ++frontend_conf.cmvn_file="${feats_dir}/data/${train_set}/am.mvn" \
           ++input="${_logdir}/keys.${JOB}.scp" \
           ++output_dir="${inference_dir}/${JOB}" \
-          ++device="${inference_device}"
+          ++device="${inference_device}" \
+          ++batch_size="${inference_batch_size}"
         }&
 
     done

examples/aishell/transformer/local/aishell_data_prep.sh

@@ -0,0 +1,66 @@
+#!/bin/bash
+
+# Copyright 2017 Xingyu Na
+# Apache 2.0
+
+#. ./path.sh || exit 1;
+
+if [ $# != 3 ]; then
+  echo "Usage: $0 <audio-path> <text-path> <output-path>"
+  echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data"
+  exit 1;
+fi
+
+aishell_audio_dir=$1
+aishell_text=$2/aishell_transcript_v0.8.txt
+output_dir=$3
+
+train_dir=$output_dir/data/local/train
+dev_dir=$output_dir/data/local/dev
+test_dir=$output_dir/data/local/test
+tmp_dir=$output_dir/data/local/tmp
+
+mkdir -p $train_dir
+mkdir -p $dev_dir
+mkdir -p $test_dir
+mkdir -p $tmp_dir
+
+# data directory check
+if [ ! -d $aishell_audio_dir ] || [ ! -f $aishell_text ]; then
+  echo "Error: $0 requires two directory arguments"
+  exit 1;
+fi
+
+# find wav audio file for train, dev and test resp.
+find $aishell_audio_dir -iname "*.wav" > $tmp_dir/wav.flist
+n=`cat $tmp_dir/wav.flist | wc -l`
+[ $n -ne 141925 ] && \
+  echo Warning: expected 141925 data data files, found $n
+
+grep -i "wav/train" $tmp_dir/wav.flist > $train_dir/wav.flist || exit 1;
+grep -i "wav/dev" $tmp_dir/wav.flist > $dev_dir/wav.flist || exit 1;
+grep -i "wav/test" $tmp_dir/wav.flist > $test_dir/wav.flist || exit 1;
+
+rm -r $tmp_dir
+
+# Transcriptions preparation
+for dir in $train_dir $dev_dir $test_dir; do
+  echo Preparing $dir transcriptions
+  sed -e 's/\.wav//' $dir/wav.flist | awk -F '/' '{print $NF}' > $dir/utt.list
+  paste -d' ' $dir/utt.list $dir/wav.flist > $dir/wav.scp_all
+  utils/filter_scp.pl -f 1 $dir/utt.list $aishell_text > $dir/transcripts.txt
+  awk '{print $1}' $dir/transcripts.txt > $dir/utt.list
+  utils/filter_scp.pl -f 1 $dir/utt.list $dir/wav.scp_all | sort -u > $dir/wav.scp
+  sort -u $dir/transcripts.txt > $dir/text
+done
+
+mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test
+
+for f in wav.scp text; do
+  cp $train_dir/$f $output_dir/data/train/$f || exit 1;
+  cp $dev_dir/$f $output_dir/data/dev/$f || exit 1;
+  cp $test_dir/$f $output_dir/data/test/$f || exit 1;
+done
+
+echo "$0: AISHELL data preparation succeeded"
+exit 0;

examples/aishell/transformer/local/download_and_untar.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+
+# Copyright   2014  Johns Hopkins University (author: Daniel Povey)
+#             2017  Xingyu Na
+# Apache 2.0
+
+remove_archive=false
+
+if [ "$1" == --remove-archive ]; then
+  remove_archive=true
+  shift
+fi
+
+if [ $# -ne 3 ]; then
+  echo "Usage: $0 [--remove-archive] <data-base> <url-base> <corpus-part>"
+  echo "e.g.: $0 /export/a05/xna/data www.openslr.org/resources/33 data_aishell"
+  echo "With --remove-archive it will remove the archive after successfully un-tarring it."
+  echo "<corpus-part> can be one of: data_aishell, resource_aishell."
+fi
+
+data=$1
+url=$2
+part=$3
+
+if [ ! -d "$data" ]; then
+  echo "$0: no such directory $data"
+  exit 1;
+fi
+
+part_ok=false
+list="data_aishell resource_aishell"
+for x in $list; do
+  if [ "$part" == $x ]; then part_ok=true; fi
+done
+if ! $part_ok; then
+  echo "$0: expected <corpus-part> to be one of $list, but got '$part'"
+  exit 1;
+fi
+
+if [ -z "$url" ]; then
+  echo "$0: empty URL base."
+  exit 1;
+fi
+
+if [ -f $data/$part/.complete ]; then
+  echo "$0: data part $part was already successfully extracted, nothing to do."
+  exit 0;
+fi
+
+# sizes of the archive files in bytes.
+sizes="15582913665 1246920"
+
+if [ -f $data/$part.tgz ]; then
+  size=$(/bin/ls -l $data/$part.tgz | awk '{print $5}')
+  size_ok=false
+  for s in $sizes; do if [ $s == $size ]; then size_ok=true; fi; done
+  if ! $size_ok; then
+    echo "$0: removing existing file $data/$part.tgz because its size in bytes $size"
+    echo "does not equal the size of one of the archives."
+    rm $data/$part.tgz
+  else
+    echo "$data/$part.tgz exists and appears to be complete."
+  fi
+fi
+
+if [ ! -f $data/$part.tgz ]; then
+  if ! command -v wget >/dev/null; then
+    echo "$0: wget is not installed."
+    exit 1;
+  fi
+  full_url=$url/$part.tgz
+  echo "$0: downloading data from $full_url.  This may take some time, please be patient."
+
+  cd $data || exit 1
+  if ! wget --no-check-certificate $full_url; then
+    echo "$0: error executing wget $full_url"
+    exit 1;
+  fi
+fi
+
+cd $data || exit 1
+
+if ! tar -xvzf $part.tgz; then
+  echo "$0: error un-tarring archive $data/$part.tgz"
+  exit 1;
+fi
+
+touch $data/$part/.complete
+
+if [ $part == "data_aishell" ]; then
+  cd $data/$part/wav || exit 1
+  for wav in ./*.tar.gz; do
+    echo "Extracting wav from $wav"
+    tar -zxf $wav && rm $wav
+  done
+fi
+
+echo "$0: Successfully downloaded and un-tarred $data/$part.tgz"
+
+if $remove_archive; then
+  echo "$0: removing $data/$part.tgz file since --remove-archive option was supplied."
+  rm $data/$part.tgz
+fi
+
+exit 0;

examples/aishell/transformer/run.sh

@@ -0,0 +1,194 @@
+#!/usr/bin/env bash
+
+
+CUDA_VISIBLE_DEVICES="0,1"
+
+# general configuration
+feats_dir="../DATA" #feature output dictionary
+exp_dir="."
+lang=zh
+token_type=char
+stage=0
+stop_stage=5
+
+# feature configuration
+nj=32
+
+inference_device="cuda" #"cpu"
+inference_checkpoint="model.pt"
+inference_scp="wav.scp"
+inference_batch_size=32
+
+# data
+raw_data=../raw_data
+data_url=www.openslr.org/resources/33
+
+# exp tag
+tag="exp1"
+workspace=`pwd`
+
+. utils/parse_options.sh || exit 1;
+
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+train_set=train
+valid_set=dev
+test_sets="dev test"
+
+config=paraformer_conformer_12e_6d_2048_256.yaml
+model_dir="baseline_$(basename "${config}" .yaml)_${lang}_${token_type}_${tag}"
+
+
+if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
+    echo "stage -1: Data Download"
+    mkdir -p ${raw_data}
+    local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
+    local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
+fi
+
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+    echo "stage 0: Data preparation"
+    # Data preparation
+    local/aishell_data_prep.sh ${raw_data}/data_aishell/wav ${raw_data}/data_aishell/transcript ${feats_dir}
+    for x in train dev test; do
+        cp ${feats_dir}/data/${x}/text ${feats_dir}/data/${x}/text.org
+        paste -d " " <(cut -f 1 -d" " ${feats_dir}/data/${x}/text.org) <(cut -f 2- -d" " ${feats_dir}/data/${x}/text.org | tr -d " ") \
+            > ${feats_dir}/data/${x}/text
+        utils/text2token.py -n 1 -s 1 ${feats_dir}/data/${x}/text > ${feats_dir}/data/${x}/text.org
+        mv ${feats_dir}/data/${x}/text.org ${feats_dir}/data/${x}/text
+
+        # convert wav.scp text to jsonl
+        scp_file_list_arg="++scp_file_list='[\"${feats_dir}/data/${x}/wav.scp\",\"${feats_dir}/data/${x}/text\"]'"
+        python ../../../funasr/datasets/audio_datasets/scp2jsonl.py \
+        ++data_type_list='["source", "target"]' \
+        ++jsonl_file_out=${feats_dir}/data/${x}/audio_datasets.jsonl \
+        ${scp_file_list_arg}
+    done
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    echo "stage 1: Feature and CMVN Generation"
+    python ../../../funasr/bin/compute_audio_cmvn.py \
+    --config-path "${workspace}/conf" \
+    --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
+fi
+
+token_list=${feats_dir}/data/${lang}_token_list/$token_type/tokens.txt
+echo "dictionary: ${token_list}"
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    echo "stage 2: Dictionary Preparation"
+    mkdir -p ${feats_dir}/data/${lang}_token_list/$token_type/
+   
+    echo "make a dictionary"
+    echo "<blank>" > ${token_list}
+    echo "<s>" >> ${token_list}
+    echo "</s>" >> ${token_list}
+    utils/text2token.py -s 1 -n 1 --space "" ${feats_dir}/data/$train_set/text | cut -f 2- -d" " | tr " " "\n" \
+        | sort | uniq | grep -a -v -e '^\s*$' | awk '{print $0}' >> ${token_list}
+    echo "<unk>" >> ${token_list}
+fi
+
+# LM Training Stage
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    echo "stage 3: LM Training"
+fi
+
+# ASR Training Stage
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+  echo "stage 4: ASR Training"
+
+  mkdir -p ${exp_dir}/exp/${model_dir}
+  log_file="${exp_dir}/exp/${model_dir}/train.log.txt"
+  echo "log_file: ${log_file}"
+
+  gpu_num=$(echo CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+  torchrun \
+  --nnodes 1 \
+  --nproc_per_node ${gpu_num} \
+  ../../../funasr/bin/train.py \
+  --config-path "${workspace}/conf" \
+  --config-name "${config}" \
+  ++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
+  ++valid_data_set_list="${feats_dir}/data/${valid_set}/audio_datasets.jsonl" \
+  ++tokenizer_conf.token_list="${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"
+
+  if ${inference_device} == "cuda"; then
+      nj=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+  else
+      inference_batch_size=1
+      CUDA_VISIBLE_DEVICES=""
+      for JOB in $(seq ${nj}); do
+          CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"-1,"
+      done
+  fi
+
+  for dset in ${test_sets}; do
+
+    inference_dir="${exp_dir}/exp/${model_dir}/${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}" ${split_scps}
+
+    gpuid_list_array=(${gpuid_list//,/ })
+    for JOB in $(seq ${nj}); do
+        {
+          id=$((JOB-1))
+          gpuid=${gpuid_list_array[$id]}
+
+          export CUDA_VISIBLE_DEVICES=${gpuid}
+          python ../../../funasr/bin/inference.py \
+          --config-path="${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}" \
+          ++batch_size="${inference_batch_size}"
+        }&
+
+    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/transformer/transformer_12e_6d_2048_256.yaml

@@ -0,0 +1,110 @@
+# This is an example that demonstrates how to configure a model file.
+# You can modify the configuration according to your own requirements.
+
+# to print the register_table:
+# from funasr.register import tables
+# tables.print()
+
+# network architecture
+model: Transformer
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1     # label smoothing option
+    length_normalized_loss: false
+
+# encoder
+encoder: TransformerEncoder
+encoder_conf:
+    output_size: 256    # dimension of attention
+    attention_heads: 4
+    linear_units: 2048  # the number of units of position-wise feed forward
+    num_blocks: 12      # the number of encoder blocks
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d # encoder architecture type
+    normalize_before: true
+
+# decoder
+decoder: TransformerDecoder
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.0
+    src_attention_dropout_rate: 0.0
+
+
+# frontend related
+frontend: WavFrontend
+frontend_conf:
+    fs: 16000
+    window: hamming
+    n_mels: 80
+    frame_length: 25
+    frame_shift: 10
+    lfr_m: 1
+    lfr_n: 1
+
+specaug: SpecAug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+
+train_conf:
+  accum_grad: 1
+  grad_clip: 5
+  max_epoch: 150
+  val_scheduler_criterion:
+      - valid
+      - acc
+  best_model_criterion:
+  -   - valid
+      - acc
+      - max
+  keep_nbest_models: 10
+  log_interval: 50
+
+optim: adam
+optim_conf:
+   lr: 0.002
+scheduler: warmuplr
+scheduler_conf:
+   warmup_steps: 30000
+
+dataset: AudioDataset
+dataset_conf:
+    index_ds: IndexDSJsonl
+    batch_sampler: DynamicBatchLocalShuffleSampler
+    batch_type: example # example or length
+    batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+    max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
+    buffer_size: 500
+    shuffle: True
+    num_workers: 0
+
+tokenizer: CharTokenizer
+tokenizer_conf:
+  unk_symbol: <unk>
+  split_with_space: true
+
+
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+normalize: null

examples/aishell/transformer/utils

@@ -0,0 +1 @@
+../paraformer/utils

funasr/tokenizer/char_tokenizer.py

@@ -50,10 +50,11 @@ class CharTokenizer(BaseTokenizer):
 	
 	def text2tokens(self, line: Union[str, list]) -> List[str]:
 		
-		if self.split_with_space:
+		# if self.split_with_space:
+		
+		if self.seg_dict is not None:
 			tokens = line.strip().split(" ")
-			if self.seg_dict is not None:
-				tokens = seg_tokenize(tokens, self.seg_dict)
+			tokens = seg_tokenize(tokens, self.seg_dict)
 		else:
 			tokens = []
 			while len(line) != 0:
@@ -66,7 +67,9 @@ class CharTokenizer(BaseTokenizer):
 				else:
 					t = line[0]
 					if t == " ":
-						t = "<space>"
+						# t = "<space>"
+						line = line[1:]
+						continue
 					tokens.append(t)
 					line = line[1:]
 		return tokens