vad : add download-vad-model scripts (#3149)

* vad : add download-vad-model scripts

This commit adds a script to download VAD models.

* vad : add vad model download script for windows [no ci]

Refs: #3146

Author: danbev

models/download-vad-model.cmd

@@ -0,0 +1,99 @@
+@echo off
+
+rem Save the original working directory
+set "orig_dir=%CD%"
+
+rem Get the script directory
+set "script_dir=%~dp0"
+
+rem Check if the script directory contains "\bin\" (case-insensitive)
+echo %script_dir% | findstr /i "\\bin\\" >nul
+if %ERRORLEVEL%==0 (
+  rem If script is in a \bin\ directory, use the original working directory as default download path
+  set "default_download_path=%orig_dir%"
+) else (
+  rem Otherwise, use script directory
+  pushd %~dp0
+  set "default_download_path=%CD%"
+  popd
+)
+
+rem Set the root path to be the parent directory of the script
+for %%d in (%~dp0..) do set "root_path=%%~fd"
+
+rem Count number of arguments passed to script
+set argc=0
+for %%x in (%*) do set /A argc+=1
+
+set models=silero-v5.1.2
+
+rem If argc is not equal to 1 or 2, print usage information and exit
+if %argc% NEQ 1 (
+  if %argc% NEQ 2 (
+    echo.
+    echo Usage: download-vad-model.cmd model [models_path]
+    CALL :list_models
+    goto :eof
+  )
+)
+
+if %argc% EQU 2 (
+  set models_path=%2
+) else (
+  set models_path=%default_download_path%
+)
+
+set model=%1
+
+for %%b in (%models%) do (
+  if "%%b"=="%model%" (
+    CALL :download_model
+    goto :eof
+  )
+)
+
+echo Invalid model: %model%
+CALL :list_models
+goto :eof
+
+:download_model
+echo Downloading vad model %model%...
+
+if exist "%models_path%\\ggml-%model%.bin" (
+  echo Model %model% already exists. Skipping download.
+  goto :eof
+)
+
+
+PowerShell -NoProfile -ExecutionPolicy Bypass -Command "Start-BitsTransfer -Source https://huggingface.co/ggml-org/whisper-vad/resolve/main/ggml-%model%.bin -Destination \"%models_path%\\ggml-%model%.bin\""
+
+if %ERRORLEVEL% neq 0 (
+  echo Failed to download ggml model %model%
+  echo Please try again later or download the original Whisper model files and convert them yourself.
+  goto :eof
+)
+
+rem Check if 'whisper-cli' is available in the system PATH
+where whisper-cli >nul 2>&1
+if %ERRORLEVEL%==0 (
+  rem If found, suggest 'whisper-cli' (relying on PATH resolution)
+  set "whisper_cmd=whisper-cli"
+) else (
+  rem If not found, suggest the local build version
+  set "whisper_cmd=%root_path%\build\bin\Release\whisper-cli.exe"
+)
+
+echo Done! Model %model% saved in %models_path%\ggml-%model%.bin
+echo You can now use it like this:
+echo %whisper_cmd% -vm %models_path%\ggml-%model%.bin --vad -m models/ggml-base.en.bin -f samples\jfk.wav
+
+goto :eof
+
+:list_models
+  echo.
+  echo Available models:
+  (for %%a in (%models%) do (
+    echo %%a
+  ))
+  echo.
+  exit /b

models/download-vad-model.sh

@@ -0,0 +1,105 @@
+#!/bin/sh
+
+# This script downloads Whisper VAD model files that have already been converted
+# to ggml format. This way you don't have to convert them yourself.
+
+src="https://huggingface.co/ggml-org/whisper-vad"
+pfx="resolve/main/ggml"
+
+BOLD="\033[1m"
+RESET='\033[0m'
+
+# get the path of this script
+get_script_path() {
+    if [ -x "$(command -v realpath)" ]; then
+        dirname "$(realpath "$0")"
+    else
+        _ret="$(cd -- "$(dirname "$0")" >/dev/null 2>&1 || exit ; pwd -P)"
+        echo "$_ret"
+    fi
+}
+
+script_path="$(get_script_path)"
+
+# Check if the script is inside a /bin/ directory
+case "$script_path" in
+    */bin) default_download_path="$PWD" ;;  # Use current directory as default download path if in /bin/
+    *) default_download_path="$script_path" ;;  # Otherwise, use script directory
+esac
+
+models_path="${2:-$default_download_path}"
+
+# Whisper VAD models
+models="silero-v5.1.2"
+
+# list available models
+list_models() {
+    printf "\n"
+    printf "Available models:"
+    model_class=""
+    for model in $models; do
+        this_model_class="${model%%[.-]*}"
+        if [ "$this_model_class" != "$model_class" ]; then
+            printf "\n "
+            model_class=$this_model_class
+        fi
+        printf " %s" "$model"
+    done
+    printf "\n\n"
+}
+
+if [ "$#" -lt 1 ] || [ "$#" -gt 2 ]; then
+    printf "Usage: %s <model> [models_path]\n" "$0"
+    list_models
+    exit 1
+fi
+
+model=$1
+
+if ! echo "$models" | grep -q -w "$model"; then
+    printf "Invalid model: %s\n" "$model"
+    list_models
+
+    exit 1
+fi
+
+# download ggml model
+printf "Downloading ggml model %s from '%s' ...\n" "$model" "$src"
+
+cd "$models_path" || exit
+
+if [ -f "ggml-$model.bin" ]; then
+    printf "Model %s already exists. Skipping download.\n" "$model"
+    exit 0
+fi
+
+if [ -x "$(command -v wget2)" ]; then
+    wget2 --no-config --progress bar -O ggml-"$model".bin $src/$pfx-"$model".bin
+elif [ -x "$(command -v wget)" ]; then
+    wget --no-config --quiet --show-progress -O ggml-"$model".bin $src/$pfx-"$model".bin
+elif [ -x "$(command -v curl)" ]; then
+    curl -L --output ggml-"$model".bin $src/$pfx-"$model".bin
+else
+    printf "Either wget or curl is required to download models.\n"
+    exit 1
+fi
+
+if [ $? -ne 0 ]; then
+    printf "Failed to download ggml model %s \n" "$model"
+    printf "Please try again later or download the original Whisper model files and convert them yourself.\n"
+    exit 1
+fi
+
+# Check if 'whisper-cli' is available in the system PATH
+if command -v whisper-cli >/dev/null 2>&1; then
+    # If found, use 'whisper-cli' (relying on PATH resolution)
+    whisper_cmd="whisper-cli"
+else
+    # If not found, use the local build version
+    whisper_cmd="./build/bin/whisper-cli"
+fi
+
+printf "Done! Model '%s' saved in '%s/ggml-%s.bin'\n" "$model" "$models_path" "$model"
+printf "You can now use it like this:\n\n"
+printf "  $ %s -vm %s/ggml-%s.bin --vad -f samples/jfk.wav -m models/ggml-base.en.bin\n" "$whisper_cmd" "$models_path" "$model"
+printf "\n"