Train from the command line

The files in the `cli` directory allow you to train wake words
from the command line without needing to use the Jupyter notebook
or a web browser.  Basically, the logic from the notebook has been
placed in separate shell scripts and python files wrapped by 3 high-level
scripts that do the following:

* setup_python_venv: Creates a Python virtual environment with all the
packages needed to train.  The venv is created in the container's /data
directory and is therefore stored on the host, not in the container's root
docker volume.

* setup_training_datasets: Downloads, extracts and converts the MIT RIR,
FMA, Audioset and Negative training reference datasets.  Also stored in /data.

* train_wake_word: Generates the wake word samples, augments them with the
audio from the training datasets, and finally runs the microwakeword training.
The resulting model tflite and json files are placed in the /data/output
directory.

See the README.md file for much more information.

cli/shell.functions

@@ -0,0 +1,150 @@
+
+if [ "$0" == "${BASH_SOURCE[0]}" ] ; then
+    echo "${BASH_SOURCE[0]} is meant to be 'sourced' not run directly" >&2
+    exit 1
+fi
+
+if [ ! -v DATA_DIR ] ; then
+    [ -f .mww-data-dir ] && DATA_DIR="${PWD}" || DATA_DIR="/data"
+fi
+
+DEFAULT_SAMPLES=20000
+DEFAULT_BATCH_SIZE=100
+DEFAULT_TRAINING_STEPS=25000
+
+[ -f "${DATA_DIR}/.defaults.env" ] && source "${DATA_DIR}/.defaults.env" || :
+
+: "${SAMPLES:=${DEFAULT_SAMPLES}}"
+: "${BATCH_SIZE:=${DEFAULT_BATCH_SIZE}}"
+: "${TRAINING_STEPS:=${DEFAULT_TRAINING_STEPS}}"
+: "${CLEANUP_WORK_DIR:=false}"
+: "${CLEANUP_ARCHIVES:=false}"
+: "${CLEANUP_INTERMEDIATE_FILES:=false}"
+: "${QUIET:=false}"
+: "${VERBOSE:=false}"
+
+HELP=false
+
+if [ -v KNOWN_ARGS ] ; then
+    KNOWN_ARGS+=( help verbose quiet h v q )
+fi
+declare -gi OPTION_COUNT=0
+declare -ga POSITIONAL_ARGS=()
+declare -ga EXTRA_ARGS=()
+declare -ga UNKNOWN_ARGS=()
+declare -i __stop_parsing=0
+for a in "$@"; do
+    if [ "$a" == "--" ] ; then
+        __stop_parsing=1
+        shift
+        continue
+    fi
+    if [ $__stop_parsing == 1 ] ; then
+        EXTRA_ARGS+=( "$a" )
+        shift
+        continue
+    fi
+
+    if [ -v KNOWN_ARGS ] && [[ "${a}" =~ ^--?([^=]+)=?.* ]] ; then
+        _arg=${BASH_REMATCH[1]}
+        known=false
+        for _k in "${KNOWN_ARGS[@]}" ; do
+            [ "${_arg}" == "${_k}" ] && { known=true ; break ; } || :
+        done
+        $known || UNKNOWN_ARGS+=( "${a}" )
+    fi
+    OPTION_COUNT+=1
+    case "$a" in
+        -h | --help)
+            HELP=true
+            break
+            ;;
+        -q | --quiet)
+            QUIET=true
+            break
+            ;;
+        -v | --verbose)
+            VERBOSE=true
+            break
+            ;;
+        --*=*)
+            [[ $a =~ --([^=]+)=(.*) ]]
+            l=${BASH_REMATCH[1]//-/_}
+            declare -n var="${l^^}"
+            var="${BASH_REMATCH[2]}"
+            ;;
+        --no-*)
+            [[ $a =~ --no-(.+) ]]
+            l=${BASH_REMATCH[1]//-/_}
+            declare -n var="${l^^}"
+            var=false
+            ;;
+        --*)
+            [[ $a =~ --(.+) ]]
+            l=${BASH_REMATCH[1]//-/_}
+            declare -n var="${l^^}"
+            var=true
+            ;;
+        *)
+            POSITIONAL_ARGS+=( "$a" )
+            ;;
+    esac
+done
+
+
+print_elapsed_time() {
+    print_seps=True
+    if [ "$1" == "--no-separators" ] ; then
+        shift
+        print_seps=False
+    fi
+    local START_TS=${1:?"Usage: $0 <start_timestamp> <end_timestamp>"}
+    local END_TS=${2:?"Usage: $0 <start_timestamp> <end_timestamp>"}
+    message="${3}"
+    python <<EOF
+from datetime import datetime
+st=datetime.fromtimestamp(int($START_TS))
+et=datetime.fromtimestamp(int($END_TS))
+msg=f"${message}  Elapsed time: {et-st!s}"
+if ${print_seps}:
+    print(f"{'=' * 80}")
+print(f"{msg:>80s}")
+if ${print_seps}:
+    print(f"{'=' * 80}")
+EOF
+}
+
+justify_text() {
+    msg="${1:?Need a string}"
+    len="${2:?Need a length}"
+    printf "%*s\n" $(( (${#msg}+len)/2)) "${msg}"
+}
+
+get_filecounts() {
+    declare -ln fca=${1}
+    local af=${2}
+    if [ -f "${af}" ] ; then
+        mapfile -t fc < <(cat "${af}")
+        for ds in "${fc[@]}" ; do
+            [[ "${ds}" =~ ^([^:]+):([0-9-]+)$ ]] && fca[${BASH_REMATCH[1]}]=${BASH_REMATCH[2]} || :
+        done
+    fi
+}
+
+get_total_filecount() {
+    declare -ln fca=${1}
+    declare -li total=0
+    for ds in "${fca[@]}" ; do
+        total+=${ds}
+    done
+    echo $total
+}
+
+write_filecounts() {
+    declare -ln fca=${1}
+    local af=${2}
+    rm -rf "${af}" || :
+    for ds in "${!fca[@]}" ; do
+        echo "${ds}:${fca[${ds}]}" >> "${af}"
+    done
+}