Merge branch 'espnet:master' into master

egs2/TEMPLATE/asr1/db.sh

@@ -60,7 +60,7 @@ MAGICDATA=downloads
 MEDIASPEECH=downloads
 MINI_LIBRISPEECH=downloads
 MISP2021=
-MSUPERB=/ocean/projects/cis210027p/shared/corpora/MultilingualSUPERB
+MLSUPERB=
 L3DAS22=
 LIBRIMIX=downloads
 LIBRITTS=

egs2/TEMPLATE/sv1/cmd.sh

@@ -0,0 +1,110 @@
+# ====== About run.pl, queue.pl, slurm.pl, and ssh.pl ======
+# Usage: <cmd>.pl [options] JOB=1:<nj> <log> <command...>
+# e.g.
+#   run.pl --mem 4G JOB=1:10 echo.JOB.log echo JOB
+#
+# Options:
+#   --time <time>: Limit the maximum time to execute.
+#   --mem <mem>: Limit the maximum memory usage.
+#   -–max-jobs-run <njob>: Limit the number parallel jobs. This is ignored for non-array jobs.
+#   --num-threads <ngpu>: Specify the number of CPU core.
+#   --gpu <ngpu>: Specify the number of GPU devices.
+#   --config: Change the configuration file from default.
+#
+# "JOB=1:10" is used for "array jobs" and it can control the number of parallel jobs.
+# The left string of "=", i.e. "JOB", is replaced by <N>(Nth job) in the command and the log file name,
+# e.g. "echo JOB" is changed to "echo 3" for the 3rd job and "echo 8" for 8th job respectively.
+# Note that the number must start with a positive number, so you can't use "JOB=0:10" for example.
+#
+# run.pl, queue.pl, slurm.pl, and ssh.pl have unified interface, not depending on its backend.
+# These options are mapping to specific options for each backend and
+# it is configured by "conf/queue.conf" and "conf/slurm.conf" by default.
+# If jobs failed, your configuration might be wrong for your environment.
+#
+#
+# The official documentation for run.pl, queue.pl, slurm.pl, and ssh.pl:
+#   "Parallelization in Kaldi": http://kaldi-asr.org/doc/queue.html
+# =========================================================~
+
+
+# Select the backend used by run.sh from "local", "stdout", "sge", "slurm", or "ssh"
+cmd_backend='local'
+
+# Local machine, without any Job scheduling system
+if [ "${cmd_backend}" = local ]; then
+
+    # The other usage
+    export train_cmd="run.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="run.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="run.pl"
+
+# Local machine logging to stdout and log file, without any Job scheduling system
+elif [ "${cmd_backend}" = stdout ]; then
+
+    # The other usage
+    export train_cmd="stdout.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="stdout.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="stdout.pl"
+
+
+# "qsub" (Sun Grid Engine, or derivation of it)
+elif [ "${cmd_backend}" = sge ]; then
+    # The default setting is written in conf/queue.conf.
+    # You must change "-q g.q" for the "queue" for your environment.
+    # To know the "queue" names, type "qhost -q"
+    # Note that to use "--gpu *", you have to setup "complex_value" for the system scheduler.
+
+    export train_cmd="queue.pl"
+    export cuda_cmd="queue.pl"
+    export decode_cmd="queue.pl"
+
+
+# "qsub" (Torque/PBS.)
+elif [ "${cmd_backend}" = pbs ]; then
+    # The default setting is written in conf/pbs.conf.
+
+    export train_cmd="pbs.pl"
+    export cuda_cmd="pbs.pl"
+    export decode_cmd="pbs.pl"
+
+
+# "sbatch" (Slurm)
+elif [ "${cmd_backend}" = slurm ]; then
+    # The default setting is written in conf/slurm.conf.
+    # You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
+    # To know the "partion" names, type "sinfo".
+    # You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
+    # The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
+
+    export train_cmd="slurm.pl"
+    export cuda_cmd="slurm.pl"
+    export decode_cmd="slurm.pl"
+
+elif [ "${cmd_backend}" = ssh ]; then
+    # You have to create ".queue/machines" to specify the host to execute jobs.
+    # e.g. .queue/machines
+    #   host1
+    #   host2
+    #   host3
+    # Assuming you can login them without any password, i.e. You have to set ssh keys.
+
+    export train_cmd="ssh.pl"
+    export cuda_cmd="ssh.pl"
+    export decode_cmd="ssh.pl"
+
+# This is an example of specifying several unique options in the JHU CLSP cluster setup.
+# Users can modify/add their own command options according to their cluster environments.
+elif [ "${cmd_backend}" = jhu ]; then
+
+    export train_cmd="queue.pl --mem 2G"
+    export cuda_cmd="queue-freegpu.pl --mem 2G --gpu 1 --config conf/queue.conf"
+    export decode_cmd="queue.pl --mem 4G"
+
+else
+    echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2
+    return 1
+fi

egs2/TEMPLATE/sv1/conf/pbs.conf

@@ -0,0 +1,11 @@
+# Default configuration
+command qsub -V -v PATH -S /bin/bash
+option name=* -N $0
+option mem=* -l mem=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -l ncpus=$0
+option num_threads=1  # Do not add anything to qsub_opts
+option num_nodes=* -l nodes=$0:ppn=1
+default gpu=0
+option gpu=0
+option gpu=* -l ngpus=$0

egs2/TEMPLATE/sv1/conf/queue.conf

@@ -0,0 +1,12 @@
+# Default configuration
+command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64*
+option name=* -N $0
+option mem=* -l mem_free=$0,ram_free=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -pe smp $0
+option num_threads=1  # Do not add anything to qsub_opts
+option max_jobs_run=* -tc $0
+option num_nodes=* -pe mpi $0  # You must set this PE as allocation_rule=1
+default gpu=0
+option gpu=0
+option gpu=* -l gpu=$0 -q g.q

egs2/TEMPLATE/sv1/conf/slurm.conf

@@ -0,0 +1,14 @@
+# Default configuration
+command sbatch --export=PATH
+option name=* --job-name $0
+option time=* --time $0
+option mem=* --mem-per-cpu $0
+option mem=0
+option num_threads=* --cpus-per-task $0
+option num_threads=1 --cpus-per-task 1
+option num_nodes=* --nodes $0
+default gpu=0
+option gpu=0 -p cpu
+option gpu=* -p gpu --gres=gpu:$0 -c $0  # Recommend allocating more CPU than, or equal to the number of GPU
+# note: the --max-jobs-run option is supported as a special case
+# by slurm.pl and you don't have to handle it in the config file.

egs2/TEMPLATE/sv1/db.sh

@@ -0,0 +1,7 @@
+# Set the path of your corpus
+# "downloads" means the corpus can be downloaded by the recipe automatically
+
+VOXCELEB1=
+VOXCELEB2=
+MUSAN=
+RIR=

egs2/TEMPLATE/sv1/path.sh

@@ -0,0 +1,23 @@
+MAIN_ROOT=$PWD/../../..
+
+export PATH=$PWD/utils/:$PATH
+export LC_ALL=C
+
+if [ -f "${MAIN_ROOT}"/tools/activate_python.sh  ]; then
+    . "${MAIN_ROOT}"/tools/activate_python.sh
+else
+    echo "[INFO] "${MAIN_ROOT}"/tools/activate_python.sh is not present"
+fi
+. "${MAIN_ROOT}"/tools/extra_path.sh
+
+export OMP_NUM_THREADS=1
+
+# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+
+# You need to change or unset NCCL_SOCKET_IFNAME according to your network environment
+# https://docs.nvidia.com/deeplearning/sdk/nccl-developer-guide/docs/env.html#nccl-socket-ifname
+export NCCL_SOCKET_IFNAME="^lo,docker,virbr,vmnet,vboxnet"
+
+# NOTE(kamo): Source at the last to overwrite the setting
+. local/path.sh

egs2/TEMPLATE/sv1/pyscripts

@@ -0,0 +1 @@
+../asr1/pyscripts

egs2/TEMPLATE/sv1/scripts/utils/print_args.sh

@@ -0,0 +1 @@
+../../../asr1/scripts/utils/print_args.sh

egs2/TEMPLATE/sv1/setup.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+# 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
+
+log() {
+    local fname=${BASH_SOURCE[1]##*/}
+    echo -e "$(date '+%Y-%m-%dT%H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+help_message=$(cat << EOF
+Usage: $0 <target-dir>
+EOF
+)
+
+
+if [ $# -ne 1 ]; then
+    log "${help_message}"
+    log "Error: 1 positional argument is required."
+    exit 2
+fi
+
+
+dir=$1
+mkdir -p "${dir}"
+
+if [ ! -d "${dir}"/../../TEMPLATE ]; then
+    log "Error: ${dir}/../../TEMPLATE should exist. You may specify wrong directory."
+    exit 1
+fi
+
+targets=""
+
+# Copy
+for f in cmd.sh conf local; do
+    target="${dir}"/../../TEMPLATE/sv1/"${f}"
+    cp -r "${target}" "${dir}"
+    targets+="${dir}/${target} "
+done
+
+
+# Symlinks to TEMPLATE/sv1
+for f in sv.sh path.sh scripts pyscripts; do
+    target=../../TEMPLATE/sv1/"${f}"
+    ln -sf "${target}" "${dir}"
+    targets+="${dir}/${target} "
+done
+
+
+# Symlinks to TEMPLATE/sv1
+for f in db.sh utils steps; do
+    target=../../TEMPLATE/sv1/"${f}"
+    ln -sf "${target}" "${dir}"
+    targets+="${dir}/${target} "
+done
+
+
+log "Created: ${targets}"

egs2/TEMPLATE/sv1/steps

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/steps

egs2/TEMPLATE/sv1/sv.sh

@@ -0,0 +1,71 @@
+#!/usr/bin/env bash
+
+# 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
+
+log() {
+    local fname=${BASH_SOURCE[1]##*/}
+        echo -e "$(date '+%Y-%m-%dT%H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+
+# General configuration
+stage=1               # Processes starts from the specified stage.
+stop_stage=10000      # Processes is stopped at the specified stage.
+skip_stages=          # Spicify the stage to be skipped
+skip_data_prep=false  # Skip data preparation stages.
+skip_train=false      # Skip training stages.
+skip_eval=false       # Skip decoding and evaluation stages.
+skip_upload=true      # Skip packing and uploading to zenodo
+skip_upload_hf=true   # Skip uploading to hugging face stages.
+eval_valid_set=false  # Run decoding for the validation set
+n_gpu=1               # The number of gpus ("0" uses cpu, otherwise use gpu).
+num_nodes=1           # The number of nodes.
+nj=32                 # The number of parallel jobs.
+inference_nj=32       # The number of parallel jobs in decoding.
+gpu_inference=false   # Whether to perform gpu decoding.
+dumpdir=dump          # Directory to dump features.
+expdir=exp            # Directory to save experiments.
+
+run_args=$(scripts/utils/print_args.sh $0 "$@")
+
+local_data_opts=
+n_train_frame=
+n_eval_frame=
+
+. utils/parse_options.sh
+
+if [ $# -ne 0  ]; then
+    log "${help_message}"
+    log "Error: No positional arguments are required."
+        exit 2
+fi
+
+. ./path.sh
+. ./cmd.sh
+
+
+if [ ${stage} -le 1  ] && [ ${stop_stage} -ge 1  ] && ! [[ " ${skip_stages} " =~ [[:space:]]1[[:space:]]  ]]; then
+    log "Stage 1: Data preparation for train and evaluation."
+    # [Task dependent] Need to create data.sh for new corpus
+    local/data.sh ${local_data_opts}
+    log "Stage 1 FIN."
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    echo "Stage 2: Train."
+    ${python} -m espnet2.bin.launch \
+        --cmd ${cuda_cmd} --name ${jobname} \
+        --log ${sv_exp}/train.log \
+        --ngpu ${ngpu} \
+        --num_nodes ${num_nodes} \
+        --init_file_prefix ${sv_exp}/.dist_init_ \
+        --multiprocessing_distributed true -- \
+        ${python} -m espnet2.bin.spk_train \
+            --use_preprocessor true \
+            --resume true \
+            --output_dir ${sv_exp} \
+            ${_opts} ${sv_args}
+fi

egs2/TEMPLATE/sv1/utils/parse_options.sh

@@ -0,0 +1 @@
+../../asr1/utils/parse_options.sh

egs2/ml_superb/asr1/README.md

@@ -16,13 +16,13 @@ Dataset are extracted from various multilingual sources. All sources are with ei
 
 ### Data download/setup
 
-[Pending]
+[Download link](https://drive.google.com/file/d/1zslKQwadZaYWXAmfBCvlos9BVQ9k6PHT/view?usp=sharing)
 
 After download the dataset, please set the `MLSUPERB` to the data directory. The preparation will be automatically done in scripts for each tasks.
 
 ### Self-supervised model setup
 
-ML-SUPERB utilizes [S3PRL]() to support different self-supervised model, supporting both the current popular self-supervised models and customized models from users.
+ML-SUPERB utilizes [S3PRL](https://github.com/s3prl/s3prl) to support different self-supervised model, supporting both the current popular self-supervised models and customized models from users.
 
 #### Existng self-supervised model
 

egs2/ml_superb/asr1/local/data.sh

@@ -43,7 +43,7 @@ log "data preparation started"
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     log "stage1: Download data to ${MLSUPERB}"
-    log "Not released yet"
+    log "Please use the download link in readme and set the MLSUPERB as its unzipped path."
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then