Kathbath asr

egs2/kathbath/asr1/asr.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/asr.sh

egs2/kathbath/asr1/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/kathbath/asr1/db.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/db.sh

egs2/kathbath/asr1/local/data.sh

@@ -0,0 +1,110 @@
+#!/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]}) $*"
+}
+SECONDS=0
+
+
+stage=1
+stop_stage=100000
+
+train_data_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/clean/train_audio.tar"
+valid_data_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/clean/valid_audio.tar"
+clean_test_known_data_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/clean/testkn_audio.tar"
+clean_test_unknown_data_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/clean/testunk_audio.tar"
+noisy_test_known_data_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/noisy/testkn_audio.tar"
+noisy_test_unknown_data_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/noisy/testunk_audio.tar"
+transcript_clean_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/clean/transcripts_n2w.tar"
+transcript_noisy_url="https://indic-asr-public.objectstore.e2enetworks.net/indic-superb/kathbath/noisy/transcripts_n2w.tar"
+
+log "$0 $*"
+. utils/parse_options.sh
+
+. ./db.sh
+. ./path.sh
+. ./cmd.sh
+
+
+if [ $# -ne 0 ]; then
+    log "Error: No positional arguments are required."
+    exit 2
+fi
+
+if [ -z "${KATHBATH}" ]; then
+    log "Fill the value of 'KATHBATH' of db.sh"
+    exit 1
+fi
+
+download_data="${KATHBATH}"
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    if [ ! -e "${KATHBATH}/download_done" ]; then
+        echo "stage 1: Data Download to ${LIBRISPEECH}"
+
+        for data_url in $noisy_test_known_data_url $noisy_test_unknown_data_url $transcript_noisy_url; do
+            if ! wget -P $download_data --no-check-certificate $data_url; then
+                echo "$0: error executing wget $data_url"
+                exit 1
+            fi
+            fname=${data_url##*/}
+            if ! tar -C $download_data -xf $download_data/$fname; then
+                echo "$0: error un-tarring archive $download_data/$fname"
+                exit 1
+            fi
+            rm $download_data/$fname
+        done
+
+        for data_url in $clean_test_known_data_url $clean_test_unknown_data_url $train_data_url $valid_data_url $transcript_clean_url; do
+            if ! wget -P $download_data --no-check-certificate $data_url; then
+                echo "$0: error executing wget $data_url"
+                exit 1
+            fi
+            fname=${data_url##*/}
+            if ! tar -C $download_data -xf $download_data/$fname; then
+                echo "$0: error un-tarring archive $download_data/$fname"
+                exit 1
+            fi
+            rm $download_data/$fname
+        done
+
+
+    touch "${KATHBATH}/download_done"
+    else
+        log "stage 1: "${KATHBATH}/download_done" is already existing. Skip data downloading"
+    fi
+fi
+
+mkdir -p data
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    if [ ! -e "data/dataprep_done" ]; then
+        log "stage 2: Data Preparation"
+
+
+        for lang in $download_data/"kb_data_clean_m4a"/* ; do
+            log "Processing $lang"
+            for split in $lang/* ; do
+
+                #https://github.com/AI4Bharat/IndicWav2Vec/blob/main/data_prep_scripts/ft_scripts/normalize_sr.sh
+                path=$split/"audio"
+                ext="wav"
+                for f in $(find "$path" -type f -name "*$ext")
+                do
+                ffmpeg -loglevel warning -hide_banner -stats -i "$f" -ar 16000 -ac 1 "$f$ext" && rm "$f" && mv "$f$ext" "$f" &
+                done
+
+            done
+        done
+
+
+        # touch "data/dataprep_done"
+    else
+        log "stage 2: "data/dataprep_done" is complete"
+    fi
+fi

egs2/kathbath/asr1/path.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/path.sh

egs2/kathbath/asr1/pyscripts

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

egs2/kathbath/asr1/scripts

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

egs2/kathbath/asr1/steps

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

egs2/kathbath/asr1/utils

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