# Stages the WER corpus for asr_bench: the first N LibriSpeech test-clean
# utterances as 16 kHz mono WAV + one reference .txt each, under bench-corpus\
# at the repo root (git-ignored — audio never enters the repo).
param([int]$Utterances = 30)
$ErrorActionPreference = "Stop"

if (-not (Get-Command ffmpeg -ErrorAction SilentlyContinue)) {
    throw "ffmpeg is required on PATH (same requirement as the app's Import feature)"
}

$repo = Split-Path -Parent (Split-Path -Parent $PSScriptRoot)
$corpus = Join-Path $repo "bench-corpus"
$cache = "$env:LOCALAPPDATA\WhispAssist\models\bench-cache"
New-Item -ItemType Directory -Force $corpus, $cache | Out-Null

$tarball = Join-Path $cache "test-clean.tar.gz"
if (-not (Test-Path $tarball)) {
    Write-Output "downloading LibriSpeech test-clean (~346 MB)"
    curl.exe -sL -o "$tarball.part" "https://www.openslr.org/resources/12/test-clean.tar.gz"
    if ($LASTEXITCODE -ne 0) { throw "download failed ($LASTEXITCODE)" }
    Move-Item -Force "$tarball.part" $tarball
}
$extracted = Join-Path $cache "LibriSpeech\test-clean"
if (-not (Test-Path $extracted)) {
    Write-Output "extracting"
    tar -xzf $tarball -C $cache
    if ($LASTEXITCODE -ne 0) { throw "extract failed ($LASTEXITCODE)" }
}

$flacs = Get-ChildItem -Recurse -Filter *.flac $extracted | Sort-Object FullName |
    Select-Object -First $Utterances
foreach ($f in $flacs) {
    $name = $f.BaseName
    $wav = Join-Path $corpus "$name.wav"
    if (-not (Test-Path $wav)) {
        ffmpeg -v error -y -i $f.FullName -ar 16000 -ac 1 $wav
        if ($LASTEXITCODE -ne 0) { throw "ffmpeg failed on $name" }
    }
    $trans = Get-ChildItem -Path $f.DirectoryName -Filter *.trans.txt | Select-Object -First 1
    $line = Get-Content $trans.FullName | Where-Object { $_.StartsWith("$name ") } | Select-Object -First 1
    if (-not $line) { throw "no reference line for $name" }
    # Named parameters on purpose: positional binding alongside -NoNewline
    # silently wrote nothing under Windows PowerShell 5.1 (found the hard way);
    # the WER normalizer doesn't care about a trailing newline.
    Set-Content -Path (Join-Path $corpus "$name.txt") -Value $line.Substring($name.Length + 1) -Encoding utf8
}
Write-Output "staged $($flacs.Count) utterances in $corpus"