Skip to content

armgit / Filee

Public Imported from GitHub
0

Free, open-source file converter. Convert 263 formats offline by drag & drop — images, PDF, Word, Excel, PowerPoint, HWP/HWPX, video, audio, e-books and archives. No upload, no Office needed.

feat: Add spoken language picker, platform neutrality, StallWatch, and polish i18n

rohitLovesKrishna02646a2c9c69
diff --git a/docs/ENGINES.md b/docs/ENGINES.md
index a4f8f70b..1e884184 100644
--- a/docs/ENGINES.md
+++ b/docs/ENGINES.md
@@ -37,7 +37,7 @@ Filee chooses engines automatically. Settings → *Engines* shows their status,
| Apple Vision | part of macOS (Mac only) | **text recognition (OCR) on a Mac**, the same step as Tesseract without a download; Tesseract reads the languages Vision doesn't (see "Apple Vision on macOS") |
| FFmpeg | **optional download** (~100 MB, 272 MB on disk) | **all video and audio**: video ↔ video (H.264, HEVC, AV1), video → animated GIF / APNG, a still frame or every frame, audio and subtitle extraction, audio ↔ audio (also APE, WavPack, TTA, DSD, DTS, ALAC, …), GIF, APNG and photos → MP4/WEBM/MOV, Live / Motion Photos → their video, a clip of a video → an iPhone Live Photo or Android Motion Photo (experimental), images → HEIC, clips or audio files joined into one, pictures → a slideshow MP4, copies without metadata (see "Media tools") |
| Calibre | **optional download** (~216 MB, 660 MB on disk) | rare e-book formats: LIT, LRF, CHM, PDB, PML, RB, SNB, TCR, OEB → EPUB; EPUB → MOBI, AZW3, LIT, LRF, PDB, PML, RB, SNB, TCR; e-books → PDF (ranked above the HWPX writer, see below) |
-| Whisper (AI Captions) | **optional download** (Windows only; ~157 MB with model, ~160 MB on disk) | **Speech-to-text transcription**: video and audio → SRT subtitles in any language using OpenAI Whisper (whisper.cpp); runs locally and offline; needs FFmpeg |
+| Whisper | **optional download** (Windows only; ~157 MB with model, ~160 MB on disk) | **Speech-to-text transcription**: video and audio → SRT subtitles in ~100 languages using OpenAI Whisper (whisper.cpp); runs locally and offline; needs FFmpeg |
DOCX, XLSX, XLS, ODS and PPTX → PDF need neither Microsoft Office nor LibreOffice: they are read in-process, written as HWPX
and rendered by rhwp. Anything the built-in readers understand (including PDF) is written as DOCX by the DOCX writer.
@@ -1762,7 +1762,7 @@ Tesseract and is registered before it, so the route planner takes it; on Windows
- Tests: `VisionLanguageTests`, `OcrTextLayerTests` and `VisionConverterTests` (a stand-in recognizer) run everywhere;
`AppleVisionTests` read real pictures on macOS (CI's Apple silicon and Intel jobs).
-## Whisper (AI Captions)
+## Whisper
Filee transcribes speech in video and audio files into SRT subtitle files using OpenAI Whisper (`whisper.cpp`).
Transcription runs entirely locally and offline on your computer; no audio or data is sent to external servers.
diff --git a/src/Filee.App/Assets/i18n/ar.json b/src/Filee.App/Assets/i18n/ar.json
index c4bfec2f..629283b9 100644
--- a/src/Filee.App/Assets/i18n/ar.json
+++ b/src/Filee.App/Assets/i18n/ar.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "التحويل بين ملفات الترجمة: SRT وASS/SSA وWebVTT وSAMI ‏(SMI) وLRC وTTML وMicroDVD وSCC، وحفظها بترميز UTF-8.\nتُقرأ ملفات SMI وSRT الكورية بترميز CP949 / EUC-KR بصورة صحيحة.",
"engine.ffmpeg.description": "الفيديو والصوت: MP4 وMOV وMKV وWEBM وMP3 وM4A وWAV وFLAC وغيرها.\nواستخراج الصوت والترجمة، وإنشاء رسوم GIF وAPNG المتحركة، وحفظ الصور بصيغة HEIC.",
- "engine.whisper.name": "Whisper (ذكاء اصطناعي مدمج)",
- "engine.whisper.description": "تحويل الكلام إلى نص مدعوم بواسطة OpenAI Whisper. يُنشئ ترجمات تلقائياً للفيديو والصوت بأي لغة.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "تحويل الكلام إلى نص مدعوم بواسطة OpenAI Whisper. يُنشئ ترجمات SRT تلقائياً من الكلام في الفيديو والصوت.",
"engine.pandoc.description": "التحويل بين Markdown وHTML وبين ODT وRTF، ومن DOCX إلى Markdown\nالتحويل بين reStructuredText وLaTeX وOrg وAsciiDoc وTypst وMediaWiki وDocBook وJupyter وغيرها وبين Markdown وHTML وDOCX وODT\nتحويل Markdown وOrg إلى شرائح PPTX",
"engine.ghostscript.description": "تحويل EPS وPostScript وملفات Illustrator القديمة إلى PDF وصور؛ وتحويل PDF إلى EPS وPS.",
"engine.tesseract.description": "يتعرّف على نص الصور والمستندات الممسوحة (OCR): PDF قابل للبحث وDOCX وTXT.",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (الأصغر، بطيء)",
"presets.hardware_encoding": "استخدام تسريع العتاد (معالج الرسوميات)",
"presets.hardware_encoding_hint": "ترميز H.264 وHEVC وAV1 باستخدام معالج الرسوميات.\nأسرع بكثير وأقل استهلاكًا للطاقة.\nالجودة أقل قليلًا عند حجم الملف نفسه.\nعند عدم توفر معالج مناسب (يتطلب AV1 معالجًا حديثًا)، يُرمَّز الفيديو بالطريقة المعتادة.",
- "presets.caption_video": "إنشاء ترجمات (Whisper AI)",
- "presets.caption_video_hint": "تحويل الكلام في الفيديو والصوت بأي لغة إلى ملف ترجمة SRT باستخدام Whisper AI.",
+ "presets.caption_video": "إنشاء ترجمات (Whisper)",
+ "presets.caption_video_hint": "تحويل الكلام في الفيديو والصوت إلى ملف ترجمة SRT باستخدام Whisper.",
+ "presets.spoken_language": "اللغة المنطوقة",
+ "presets.spoken_language.auto": "تلقائي",
"presets.audio_codec": "ترميز الصوت",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (دون فقدان)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (الفيديو والصوت)",
"engines.package.ffmpeg.description": "يضيف تحويل الفيديو والصوت، وتحويل الفيديو إلى GIF أو صورة ثابتة، واستخراج الصوت من الفيديو، وتحويل GIF إلى MP4.\nمطلوب للفيديو والصوت فقط.",
"engines.package.whisper.name": "Whisper (ترجمة بالذكاء الاصطناعي)",
- "engines.package.whisper.description": "تحويل الكلام في الفيديو والصوت بأي لغة إلى ملفات ترجمة SRT.",
+ "engines.package.whisper.description": "تحويل الكلام في الفيديو والصوت إلى ملفات ترجمة SRT. يعمل بدون اتصال بالإنترنت.",
"engines.package.calibre.name": "Calibre (Kindle وصيغ الكتب النادرة)",
"engines.package.calibre.description": "يحفظ MOBI وAZW3 لأجهزة Kindle، ويحوّل صيغ الكتب الإلكترونية النادرة (LIT وLRF وPDB وCHM…).\nتُقرأ EPUB وMOBI وAZW3 وFB2 والقصص المصورة بدونه.",
"engines.package.size": "التنزيل {0} · على القرص {1}",
diff --git a/src/Filee.App/Assets/i18n/de.json b/src/Filee.App/Assets/i18n/de.json
index 6f35ea27..42e50af9 100644
--- a/src/Filee.App/Assets/i18n/de.json
+++ b/src/Filee.App/Assets/i18n/de.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Untertitel (integriert)",
"engine.subtitle.description": "Untertitel: Konvertiert SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD und SCC untereinander und speichert sie als UTF-8.\nKoreanische SMI- und SRT-Dateien in CP949 / EUC-KR werden korrekt gelesen.",
"engine.ffmpeg.description": "Video und Audio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC und mehr.\nExtrahiert auch Ton und Untertitel, erstellt GIF- und APNG-Animationen und speichert Bilder als HEIC.",
- "engine.whisper.name": "Whisper (integrierte KI)",
- "engine.whisper.description": "Sprache-zu-Text-Transkription powered by OpenAI Whisper. Erstellt automatisch Untertitel für Videos und Audio in jeder Sprache.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Sprache-zu-Text-Transkription powered by OpenAI Whisper. Erstellt automatisch SRT-Untertitel aus Sprache in Video und Audio.",
"engine.pandoc.description": "Markdown und HTML ↔ ODT und RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter und mehr ↔ Markdown, HTML, DOCX und ODT\nMarkdown und Org → PPTX-Folien",
"engine.ghostscript.description": "EPS, PostScript und ältere Illustrator-Dateien in PDF und Bilder; PDF in EPS und PS.",
"engine.tesseract.description": "Erkennt Text in Scans und Bildern (OCR): durchsuchbare PDF, DOCX, TXT.",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (am kleinsten, langsam)",
"presets.hardware_encoding": "Hardwarebeschleunigung nutzen (Grafikchip)",
"presets.hardware_encoding_hint": "Kodiert H.264, HEVC und AV1 auf dem Grafikchip.\nDeutlich schneller und stromsparender.\nEtwas geringere Qualität bei gleicher Dateigröße.\nOhne geeigneten Chip (AV1 benötigt einen neueren) wird das Video wie gewohnt kodiert.",
- "presets.caption_video": "Untertitel erstellen (Whisper KI)",
- "presets.caption_video_hint": "Transkribiert Sprache in Videos und Audio in beliebigen Sprachen mit Whisper KI in eine SRT-Untertiteldatei.",
+ "presets.caption_video": "Untertitel erstellen (Whisper)",
+ "presets.caption_video_hint": "Transkribiert Sprache in Videos und Audio mit Whisper in eine SRT-Untertiteldatei.",
+ "presets.spoken_language": "Gesprochene Sprache",
+ "presets.spoken_language.auto": "Automatisch",
"presets.audio_codec": "Audio-Codec",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (verlustfrei)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (Video und Audio)",
"engines.package.ffmpeg.description": "Ergänzt Video- und Audiokonvertierung, Video → GIF oder Einzelbild, Ton aus Videos und GIF → MP4.\nNur für Video und Audio erforderlich.",
"engines.package.whisper.name": "Whisper (KI-Untertitel)",
- "engines.package.whisper.description": "Transkribiert Sprache in Videos und Audio in beliebigen Sprachen in SRT-Untertiteldateien.",
+ "engines.package.whisper.description": "Transkribiert Sprache in Videos und Audio in SRT-Untertiteldateien. Funktioniert offline ohne Internetverbindung.",
"engines.package.calibre.name": "Calibre (Kindle und seltene E-Book-Formate)",
"engines.package.calibre.description": "Speichert MOBI und AZW3 für Kindle und konvertiert seltene E-Book-Formate (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 und Comics lassen sich auch ohne Calibre lesen.",
"engines.package.size": "Download {0} · Platzbedarf {1}",
diff --git a/src/Filee.App/Assets/i18n/en.json b/src/Filee.App/Assets/i18n/en.json
index 50ef618c..9409ad79 100644
--- a/src/Filee.App/Assets/i18n/en.json
+++ b/src/Filee.App/Assets/i18n/en.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "Subtitles: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD and SCC into each other, saved as UTF-8.\nKorean SMI and SRT files in CP949 / EUC-KR read correctly.",
"engine.ffmpeg.description": "Video and audio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC and more.\nAlso extracts sound and subtitles, makes GIF and APNG animations and saves images as HEIC.",
- "engine.whisper.name": "Whisper (built-in AI)",
- "engine.whisper.description": "Speech-to-text transcription powered by OpenAI Whisper. Automatically generates subtitles for video and audio in any language.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Speech-to-text transcription powered by OpenAI Whisper. Automatically generates SRT subtitles from speech in video and audio.",
"engine.pandoc.description": "Markdown and HTML ↔ ODT and RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter and more ↔ Markdown, HTML, DOCX and ODT\nMarkdown and Org → PPTX slides",
"engine.ghostscript.description": "EPS, PostScript and older Illustrator files to PDF and images; PDF to EPS and PS.",
"engine.tesseract.description": "Recognizes the text of scans and pictures (OCR): searchable PDF, DOCX, TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (smallest, slow)",
"presets.hardware_encoding": "Use hardware acceleration (graphics chip)",
"presets.hardware_encoding_hint": "Encodes H.264, HEVC and AV1 on the graphics chip.\nMuch faster and uses less power.\nSlightly lower quality at the same file size.\nWithout a usable chip (AV1 needs a recent one), the video is encoded as usual.",
- "presets.caption_video": "Generate subtitles (Whisper AI)",
- "presets.caption_video_hint": "Transcribes speech in videos and audio in any language to an SRT subtitle file using Whisper AI.",
+ "presets.caption_video": "Generate subtitles (Whisper)",
+ "presets.caption_video_hint": "Transcribes speech in videos and audio to an SRT subtitle file using Whisper.",
+ "presets.spoken_language": "Spoken language",
+ "presets.spoken_language.auto": "Auto",
"presets.audio_codec": "Audio codec",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (lossless)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (video and audio)",
"engines.package.ffmpeg.description": "Adds video and audio conversion, video → GIF or still image, sound from videos and GIF → MP4.\nOnly needed for video and audio.",
"engines.package.whisper.name": "Whisper (AI Captions)",
- "engines.package.whisper.description": "Transcribes speech in video and audio in any language to SRT subtitle files.",
+ "engines.package.whisper.description": "Transcribes speech in video and audio to SRT subtitle files. Runs offline without an internet connection.",
"engines.package.calibre.name": "Calibre (Kindle and rare e-book formats)",
"engines.package.calibre.description": "Saves MOBI and AZW3 for Kindle and converts rare e-book formats (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 and comics are read without it.",
"engines.package.size": "Download {0} · {1} on disk",
diff --git a/src/Filee.App/Assets/i18n/es.json b/src/Filee.App/Assets/i18n/es.json
index 0d87fef6..3992589a 100644
--- a/src/Filee.App/Assets/i18n/es.json
+++ b/src/Filee.App/Assets/i18n/es.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "Subtítulos: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD y SCC entre sí, guardados como UTF-8.\nLee correctamente archivos SMI y SRT coreanos en CP949 / EUC-KR.",
"engine.ffmpeg.description": "Vídeo y audio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC y más.\nTambién extrae sonido y subtítulos, crea animaciones GIF y APNG y guarda imágenes como HEIC.",
- "engine.whisper.name": "Whisper (IA integrada)",
- "engine.whisper.description": "Transcripción de voz a texto con OpenAI Whisper. Genera subtítulos automáticamente para vídeo y audio en cualquier idioma.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Transcripción de voz a texto con OpenAI Whisper. Genera automáticamente subtítulos SRT a partir de voz en vídeo y audio.",
"engine.pandoc.description": "Markdown y HTML ↔ ODT y RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter y más ↔ Markdown, HTML, DOCX y ODT\nMarkdown y Org → diapositivas PPTX",
"engine.ghostscript.description": "EPS, PostScript y archivos antiguos de Illustrator a PDF e imágenes; PDF a EPS y PS.",
"engine.tesseract.description": "Reconoce el texto de escaneos e imágenes (OCR): PDF con búsqueda, DOCX, TXT.",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (el más pequeño, lento)",
"presets.hardware_encoding": "Usar aceleración por hardware (chip gráfico)",
"presets.hardware_encoding_hint": "Codifica H.264, HEVC y AV1 en el chip gráfico.\nMucho más rápido y consume menos energía.\nCalidad ligeramente inferior con el mismo tamaño de archivo.\nSin un chip compatible (AV1 necesita uno reciente), el vídeo se codifica de la forma habitual.",
- "presets.caption_video": "Generar subtítulos (Whisper IA)",
- "presets.caption_video_hint": "Transcribe la voz de vídeos y audios en cualquier idioma a un archivo de subtítulos SRT usando Whisper IA.",
+ "presets.caption_video": "Generar subtítulos (Whisper)",
+ "presets.caption_video_hint": "Transcribe la voz de vídeos y audios a un archivo de subtítulos SRT usando Whisper.",
+ "presets.spoken_language": "Idioma hablado",
+ "presets.spoken_language.auto": "Automático",
"presets.audio_codec": "Códec de audio",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (sin pérdida)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (vídeo y audio)",
"engines.package.ffmpeg.description": "Añade conversión de vídeo y audio, vídeo → GIF o imagen fija, sonido de vídeos y GIF → MP4.\nSolo es necesario para vídeo y audio.",
"engines.package.whisper.name": "Whisper (subtítulos IA)",
- "engines.package.whisper.description": "Transcribe la voz de vídeos y audios en cualquier idioma a archivos de subtítulos SRT.",
+ "engines.package.whisper.description": "Transcribe la voz de vídeos y audios a archivos de subtítulos SRT. Funciona sin conexión a internet.",
"engines.package.calibre.name": "Calibre (Kindle y libros electrónicos poco habituales)",
"engines.package.calibre.description": "Guarda MOBI y AZW3 para Kindle y convierte formatos de libro electrónico poco habituales (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 y cómics se leen sin él.",
"engines.package.size": "Descargar {0} · {1} en disco",
diff --git a/src/Filee.App/Assets/i18n/fr.json b/src/Filee.App/Assets/i18n/fr.json
index ed72d412..ac6157ea 100644
--- a/src/Filee.App/Assets/i18n/fr.json
+++ b/src/Filee.App/Assets/i18n/fr.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "Sous-titres : SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD et SCC entre eux, enregistrés en UTF-8.\nLes fichiers SMI et SRT coréens en CP949 / EUC-KR sont lus correctement.",
"engine.ffmpeg.description": "Vidéo et audio : MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC et plus.\nExtrait aussi le son et les sous-titres, crée des animations GIF et APNG et enregistre des images en HEIC.",
- "engine.whisper.name": "Whisper (IA intégrée)",
- "engine.whisper.description": "Transcription parole-texte optimisée par OpenAI Whisper. Génère automatiquement des sous-titres pour les vidéos et audios dans toutes les langues.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Transcription parole-texte optimisée par OpenAI Whisper. Génère automatiquement des sous-titres SRT à partir de la voix dans les vidéos et audios.",
"engine.pandoc.description": "Markdown et HTML ↔ ODT et RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter et plus ↔ Markdown, HTML, DOCX et ODT\nMarkdown et Org → diapositives PPTX",
"engine.ghostscript.description": "EPS, PostScript et anciens fichiers Illustrator en PDF et images ; PDF en EPS et PS.",
"engine.tesseract.description": "Reconnaît le texte des numérisations et des images (OCR) : PDF consultable, DOCX, TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (le plus léger, lent)",
"presets.hardware_encoding": "Utiliser l'accélération matérielle (puce graphique)",
"presets.hardware_encoding_hint": "Encode le H.264, le HEVC et l'AV1 sur la puce graphique.\nBeaucoup plus rapide et moins gourmand en énergie.\nQualité légèrement inférieure à taille de fichier égale.\nSans puce compatible (l'AV1 en exige une récente), la vidéo est encodée normalement.",
- "presets.caption_video": "Générer des sous-titres (Whisper IA)",
- "presets.caption_video_hint": "Transcrit la parole des vidéos et audios dans n'importe quelle langue en un fichier de sous-titres SRT avec Whisper IA.",
+ "presets.caption_video": "Générer des sous-titres (Whisper)",
+ "presets.caption_video_hint": "Transcrit la parole des vidéos et audios en un fichier de sous-titres SRT à l'aide de Whisper.",
+ "presets.spoken_language": "Langue parlée",
+ "presets.spoken_language.auto": "Automatique",
"presets.audio_codec": "Codec audio",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (sans perte)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (vidéo et audio)",
"engines.package.ffmpeg.description": "Ajoute la conversion vidéo et audio, vidéo → GIF ou image fixe, le son des vidéos et GIF → MP4.\nNécessaire uniquement pour la vidéo et l'audio.",
"engines.package.whisper.name": "Whisper (sous-titres IA)",
- "engines.package.whisper.description": "Transcrit la parole des vidéos et audios dans toutes les langues en fichiers de sous-titres SRT.",
+ "engines.package.whisper.description": "Transcrit la parole des vidéos et audios en fichiers de sous-titres SRT. Fonctionne hors ligne sans connexion Internet.",
"engines.package.calibre.name": "Calibre (Kindle et formats de livres numériques rares)",
"engines.package.calibre.description": "Enregistre en MOBI et AZW3 pour Kindle et convertit les formats de livres numériques rares (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 et bandes dessinées sont lus sans lui.",
"engines.package.size": "Téléchargement {0} · {1} sur le disque",
diff --git a/src/Filee.App/Assets/i18n/hi.json b/src/Filee.App/Assets/i18n/hi.json
index 2ff5fc09..e1f1c4e1 100644
--- a/src/Filee.App/Assets/i18n/hi.json
+++ b/src/Filee.App/Assets/i18n/hi.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "सबटाइटल: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD और SCC एक-दूसरे में, UTF-8 में सहेजे जाते हैं।\nCP949 / EUC-KR में कोरियाई SMI और SRT फ़ाइलें सही पढ़ी जाती हैं।",
"engine.ffmpeg.description": "वीडियो और ऑडियो: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC और अन्य।\nआवाज़ और सबटाइटल निकालता है, GIF और APNG एनिमेशन बनाता है और इमेज को HEIC में सहेजता है।",
- "engine.whisper.name": "Whisper (अंतर्निहित AI)",
- "engine.whisper.description": "OpenAI Whisper द्वारा संचालित स्पीच-टू-टेक्स्ट ट्रांसक्रिप्शन। किसी भी भाषा में वीडियो और ऑडियो के लिए स्वचालित रूप से उपशीर्षक बनाता है।",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "OpenAI Whisper द्वारा संचालित स्पीच-टू-टेक्स्ट ट्रांसक्रिप्शन। वीडियो और ऑडियो में भाषण से स्वचालित रूप से SRT उपशीर्षक बनाता है।",
"engine.pandoc.description": "Markdown और HTML ↔ ODT और RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter और अन्य ↔ Markdown, HTML, DOCX और ODT\nMarkdown और Org → PPTX स्लाइड",
"engine.ghostscript.description": "EPS, PostScript और पुरानी Illustrator फ़ाइलें PDF और इमेज में; PDF से EPS और PS।",
"engine.tesseract.description": "स्कैन और तस्वीरों का टेक्स्ट पहचानता है (OCR): खोजने योग्य PDF, DOCX, TXT।",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (सबसे छोटा, धीमा)",
"presets.hardware_encoding": "हार्डवेयर एक्सेलरेशन इस्तेमाल करें (ग्राफ़िक्स चिप)",
"presets.hardware_encoding_hint": "H.264, HEVC और AV1 को ग्राफ़िक्स चिप पर एन्कोड करता है।\nबहुत तेज़ है और कम बिजली लगती है।\nउसी फ़ाइल साइज़ पर क्वालिटी थोड़ी कम होती है।\nउपयोगी चिप न होने पर (AV1 के लिए नई चिप चाहिए) वीडियो सामान्य तरीके से एन्कोड होता है।",
- "presets.caption_video": "उपशीर्षक बनाएं (Whisper AI)",
- "presets.caption_video_hint": "Whisper AI का उपयोग करके किसी भी भाषा में वीडियो और ऑडियो के भाषण को SRT उपशीर्षक फ़ाइल में ट्रांसक्राइब करता है।",
+ "presets.caption_video": "उपशीर्षक बनाएं (Whisper)",
+ "presets.caption_video_hint": "Whisper का उपयोग करके वीडियो और ऑडियो में भाषण को SRT उपशीर्षक फ़ाइल में ट्रांसक्राइब करता है।",
+ "presets.spoken_language": "बोली जाने वाली भाषा",
+ "presets.spoken_language.auto": "स्वचालित",
"presets.audio_codec": "ऑडियो कोडेक",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (लॉसलेस)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (वीडियो और ऑडियो)",
"engines.package.ffmpeg.description": "वीडियो और ऑडियो कन्वर्ज़न, वीडियो → GIF या स्टिल इमेज, वीडियो से आवाज़ और GIF → MP4 जोड़ता है।\nकेवल वीडियो और ऑडियो के लिए ज़रूरी।",
"engines.package.whisper.name": "Whisper (AI उपशीर्षक)",
- "engines.package.whisper.description": "किसी भी भाषा में वीडियो और ऑडियो के भाषण को SRT उपशीर्षक फ़ाइलों में ट्रांसक्राइब करता है।",
+ "engines.package.whisper.description": "वीडियो और ऑडियो के भाषण को SRT उपशीर्षक फ़ाइलों में ट्रांसक्राइब करता है। इंटरनेट कनेक्शन के बिना ऑफ़लाइन काम करता है।",
"engines.package.calibre.name": "Calibre (Kindle और दुर्लभ ई-बुक फ़ॉर्मैट)",
"engines.package.calibre.description": "Kindle के लिए MOBI और AZW3 सहेजता है और दुर्लभ ई-बुक फ़ॉर्मैट (LIT, LRF, PDB, CHM…) कन्वर्ट करता है।\nEPUB, MOBI, AZW3, FB2 और कॉमिक्स इसके बिना भी पढ़े जाते हैं।",
"engines.package.size": "डाउनलोड {0} · डिस्क पर {1}",
diff --git a/src/Filee.App/Assets/i18n/it.json b/src/Filee.App/Assets/i18n/it.json
index 3b00c016..325483f5 100644
--- a/src/Filee.App/Assets/i18n/it.json
+++ b/src/Filee.App/Assets/i18n/it.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Sottotitoli (integrato)",
"engine.subtitle.description": "Sottotitoli: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD e SCC convertibili tra loro, salvati in UTF-8.\\nI file SMI e SRT coreani in CP949 / EUC-KR vengono letti correttamente.",
"engine.ffmpeg.description": "Video e audio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC e altro.\\nEstrae anche l'audio e i sottotitoli, crea animazioni GIF e APNG e salva le immagini come HEIC.",
- "engine.whisper.name": "Whisper (IA integrata)",
- "engine.whisper.description": "Trascrizione vocale con tecnologia OpenAI Whisper. Genera automaticamente sottotitoli per video e audio in qualsiasi lingua.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Trascrizione vocale con tecnologia OpenAI Whisper. Genera automaticamente sottotitoli SRT dal parlato in video e audio.",
"engine.pandoc.description": "Markdown e HTML ↔ ODT e RTF, DOCX → Markdown\\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter e altro ↔ Markdown, HTML, DOCX e ODT\\nMarkdown e Org → slide PPTX",
"engine.ghostscript.description": "EPS, PostScript e vecchi file Illustrator in PDF e immagini; PDF in EPS e PS.",
"engine.tesseract.description": "Riconosce il testo di scansioni e immagini (OCR): PDF ricercabile, DOCX, TXT.",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (il più piccolo, lento)",
"presets.hardware_encoding": "Usa l'accelerazione hardware (chip grafico)",
"presets.hardware_encoding_hint": "Codifica H.264, HEVC e AV1 sul chip grafico.\\nMolto più veloce e consuma meno energia.\\nQualità leggermente inferiore a parità di dimensione del file.\\nSenza un chip utilizzabile (AV1 ne richiede uno recente), il video viene codificato normalmente.",
- "presets.caption_video": "Genera sottotitoli (Whisper IA)",
- "presets.caption_video_hint": "Trascrive la voce in video e audio in qualsiasi lingua in un file di sottotitoli SRT usando Whisper IA.",
+ "presets.caption_video": "Genera sottotitoli (Whisper)",
+ "presets.caption_video_hint": "Trascrive la voce in video e audio in un file di sottotitoli SRT utilizzando Whisper.",
+ "presets.spoken_language": "Lingua parlata",
+ "presets.spoken_language.auto": "Automatico",
"presets.audio_codec": "Codec audio",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (senza perdita)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (video e audio)",
"engines.package.ffmpeg.description": "Aggiunge la conversione di video e audio, video → GIF o immagine fissa, audio dai video e GIF → MP4.\\nServe solo per video e audio.",
"engines.package.whisper.name": "Whisper (sottotitoli IA)",
- "engines.package.whisper.description": "Trascrive la voce in video e audio in qualsiasi lingua in file di sottotitoli SRT.",
+ "engines.package.whisper.description": "Trascrive la voce in video e audio in file di sottotitoli SRT. Funziona offline senza connessione Internet.",
"engines.package.calibre.name": "Calibre (Kindle e formati di e-book rari)",
"engines.package.calibre.description": "Salva MOBI e AZW3 per Kindle e converte formati di e-book rari (LIT, LRF, PDB, CHM…).\\nEPUB, MOBI, AZW3, FB2 e fumetti si leggono senza.",
"engines.package.size": "Download {0} · {1} su disco",
diff --git a/src/Filee.App/Assets/i18n/ja.json b/src/Filee.App/Assets/i18n/ja.json
index 01f68110..04d00325 100644
--- a/src/Filee.App/Assets/i18n/ja.json
+++ b/src/Filee.App/Assets/i18n/ja.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "字幕形式(SRT、ASS/SSA、WebVTT、SAMI(SMI)、LRC、TTML、MicroDVD、SCC)を相互変換し、UTF-8で保存します。\nCP949 / EUC-KRの韓国語SMI、SRTファイルも正しく読み込めます。",
"engine.ffmpeg.description": "動画と音声(MP4、MOV、MKV、WEBM、MP3、M4A、WAV、FLACなど)を変換します。\n音声や字幕の抽出、GIFやAPNGアニメーションの作成、画像のHEIC保存にも対応します。",
- "engine.whisper.name": "Whisper (内蔵AI)",
- "engine.whisper.description": "OpenAI Whisperによる音声テキスト変換。あらゆる言語の動画や音声の字幕を自動生成します。",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "OpenAI Whisperによる音声テキスト変換。動画や音声の音声をSRT字幕ファイルに自動生成します。",
"engine.pandoc.description": "Markdown、HTMLとODT、RTFを相互変換し、DOCXをMarkdownに変換します。\nreStructuredText、LaTeX、Org、AsciiDoc、Typst、MediaWiki、DocBook、JupyterなどをMarkdown、HTML、DOCX、ODTと相互変換します。\nMarkdown、OrgからPPTXスライドを作成します。",
"engine.ghostscript.description": "EPS、PostScript、古いIllustratorファイルをPDFや画像に変換し、PDFをEPSやPSに変換します。",
"engine.tesseract.description": "スキャンや画像の文字を認識します(OCR):検索可能な PDF、DOCX、TXT。",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1(最小、変換に時間がかかる)",
"presets.hardware_encoding": "ハードウェアアクセラレーションを使う(GPU)",
"presets.hardware_encoding_hint": "GPUでH.264、HEVC、AV1にエンコードします。\n大幅に速くなり、消費電力も抑えられます。\n同じファイルサイズでは、画質がわずかに低くなります。\n利用可能なGPUがない場合(AV1には新しいGPUが必要です)は、通常の方法でエンコードします。",
- "presets.caption_video": "字幕を生成 (Whisper AI)",
- "presets.caption_video_hint": "Whisper AIを使用して動画や音声の音声をあらゆる言語のSRT字幕ファイルに変換します。",
+ "presets.caption_video": "字幕を生成 (Whisper)",
+ "presets.caption_video_hint": "Whisperを使用して動画や音声の音声をSRT字幕ファイルに書き起こします。",
+ "presets.spoken_language": "音声言語",
+ "presets.spoken_language.auto": "自動",
"presets.audio_codec": "音声コーデック",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC(可逆圧縮)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg(動画・音声)",
"engines.package.ffmpeg.description": "動画・音声の変換、動画 → GIF・静止画、動画からの音声抽出、GIF → MP4に対応します。\n動画と音声の変換にのみ必要です。",
"engines.package.whisper.name": "Whisper (AI字幕)",
- "engines.package.whisper.description": "あらゆる言語の動画や音声の音声をSRT字幕ファイルに書き起こします。",
+ "engines.package.whisper.description": "動画や音声の音声をSRT字幕ファイルに書き起こします。インターネット接続なしでオフラインで動作します。",
"engines.package.calibre.name": "Calibre(Kindle形式・一般的でない電子書籍形式)",
"engines.package.calibre.description": "Kindle用にMOBI、AZW3形式で保存できるほか、一般的でない電子書籍形式(LIT、LRF、PDB、CHMなど)を変換できます。\nEPUB、MOBI、AZW3、FB2、コミックの読み込みには、このエンジンは必要ありません。",
"engines.package.size": "ダウンロード:{0} · ディスク使用量:{1}",
diff --git a/src/Filee.App/Assets/i18n/ko.json b/src/Filee.App/Assets/i18n/ko.json
index f4bc7fae..6cf8dddc 100644
--- a/src/Filee.App/Assets/i18n/ko.json
+++ b/src/Filee.App/Assets/i18n/ko.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "SRT, ASS/SSA, WebVTT, SAMI(SMI), LRC, TTML, MicroDVD, SCC 자막을 서로 바꾸고 UTF-8로 저장해요.\nCP949/EUC-KR로 된 SMI·SRT 파일도 한글이 깨지지 않아요.",
"engine.ffmpeg.description": "MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC 등 동영상·오디오를 변환해요.\n소리·자막 추출, GIF·APNG 만들기, 이미지 → HEIC도 해요.",
- "engine.whisper.name": "Whisper (내장 AI)",
- "engine.whisper.description": "OpenAI Whisper 기반 음성 텍스트 변환. 모든 언어의 비디오 및 오디오 자막을 자동으로 생성합니다.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "OpenAI Whisper 기반 음성 텍스트 변환. 동영상과 오디오의 말소리를 SRT 자막 파일로 바꿔요.",
"engine.pandoc.description": "마크다운·HTML ↔ ODT·RTF, DOCX → 마크다운\nreStructuredText·LaTeX·Org·AsciiDoc·Typst·MediaWiki·DocBook·Jupyter 등 ↔ 마크다운·HTML·DOCX·ODT\n마크다운·Org → PPTX 슬라이드",
"engine.ghostscript.description": "EPS, 포스트스크립트, 예전 일러스트레이터 파일을 PDF와 이미지로, PDF를 EPS·PS로.",
"engine.tesseract.description": "스캔본과 사진의 글자를 인식해요(OCR): 검색 가능한 PDF, DOCX, TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (가장 작게, 느림)",
"presets.hardware_encoding": "하드웨어 가속 사용 (그래픽 칩)",
"presets.hardware_encoding_hint": "H.264, HEVC, AV1을 그래픽 칩으로 인코딩해요.\n훨씬 빠르고 전력도 덜 써요.\n같은 용량이면 화질이 조금 낮아요.\n쓸 수 있는 칩이 없으면(AV1은 최신 칩이 필요해요) 평소처럼 인코딩해요.",
- "presets.caption_video": "자막 생성 (Whisper AI)",
- "presets.caption_video_hint": "Whisper AI를 사용하여 비디오 및 오디오의 음성을 모든 언어의 SRT 자막 파일로 변환합니다.",
+ "presets.caption_video": "자막 생성 (Whisper)",
+ "presets.caption_video_hint": "Whisper로 비디오와 오디오의 말소리를 SRT 자막 파일로 변환해요.",
+ "presets.spoken_language": "음성 언어",
+ "presets.spoken_language.auto": "자동",
"presets.audio_codec": "오디오 코덱",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (무손실)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (동영상·오디오)",
"engines.package.ffmpeg.description": "동영상·오디오 변환, 동영상 → GIF·정지 이미지, 소리 추출, GIF → MP4를 추가해요.\n동영상과 오디오에만 필요해요.",
"engines.package.whisper.name": "Whisper (AI 자막)",
- "engines.package.whisper.description": "모든 언어의 비디오 및 오디오 음성을 SRT 자막 파일로 변환합니다.",
+ "engines.package.whisper.description": "동영상과 오디오의 말소리를 SRT 자막 파일로 바꿔요. 인터넷 연결 없이 작동해요.",
"engines.package.calibre.name": "Calibre (킨들과 드문 전자책 형식)",
"engines.package.calibre.description": "킨들용 MOBI·AZW3로 저장하고, 드문 전자책 형식(LIT, LRF, PDB, CHM 등)을 변환해요.\nEPUB·MOBI·AZW3·FB2와 만화책은 없어도 읽어요.",
"engines.package.size": "다운로드 {0} · 설치 후 {1}",
diff --git a/src/Filee.App/Assets/i18n/ne.json b/src/Filee.App/Assets/i18n/ne.json
index fc5b9a03..058bbb47 100644
--- a/src/Filee.App/Assets/i18n/ne.json
+++ b/src/Filee.App/Assets/i18n/ne.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "उपशीर्षकहरू: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD र SCC एकअर्कामा, UTF-8 मा सुरक्षित गरिन्छ।\nCP949 / EUC-KR मा कोरियाली SMI र SRT फाइलहरू सही रूपमा पढ्छ।",
"engine.ffmpeg.description": "भिडियो र अडियो: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC र थप।\nध्वनि र उपशीर्षक पनि निकाल्छ, GIF र APNG एनिमेसन बनाउँछ र छविहरूलाई HEIC मा सुरक्षित गर्दछ।",
- "engine.whisper.name": "Whisper (अन्तर्निहित AI)",
- "engine.whisper.description": "OpenAI Whisper द्वारा सञ्चालित स्पीच-टु-टेक्स्ट ट्रान्सक्रिप्सन। कुनै पनि भाषामा भिडियो र अडियोको लागि स्वचालित रूपमा उपशीर्षकहरू उत्पन्न गर्दछ।",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "OpenAI Whisper द्वारा सञ्चालित स्पीच-टु-टेक्स्ट ट्रान्सक्रिप्सन। भिडियो र अडियोमा भएको भाषणबाट स्वचालित रूपमा SRT उपशीर्षकहरू उत्पन्न गर्दछ।",
"engine.pandoc.description": "Markdown र HTML ↔ ODT र RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter र थप ↔ Markdown, HTML, DOCX र ODT\nMarkdown र Org → PPTX स्लाइडहरू",
"engine.ghostscript.description": "EPS, PostScript र पुराना Illustrator फाइलहरूलाई PDF र छविहरूमा; PDF लाई EPS र PS मा।",
"engine.tesseract.description": "स्क्यान र तस्बिरको पाठ पहिचान गर्छ (OCR): खोज्न मिल्ने PDF, DOCX, TXT।",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (सबैभन्दा सानो, सुस्त)",
"presets.hardware_encoding": "हार्डवेयर इन्कोडिङ प्रयोग गर्नुहोस्",
"presets.hardware_encoding_hint": "H.264, HEVC र AV1 लाई ग्राफिक्स चिपमा इन्कोड गर्दछ।\nधेरै छिटो हुन्छ र कम पावर खपत गर्छ।\nसमान फाइल साइजमा गुणस्तर थोरै कम हुन्छ।\nप्रयोगयोग्य चिप नभएमा (AV1 का लागि नयाँ चिप चाहिन्छ), भिडियो सामान्य तरिकाले इन्कोड हुन्छ।",
- "presets.caption_video": "उपशीर्षक उत्पन्न गर्नुहोस् (Whisper AI)",
- "presets.caption_video_hint": "Whisper AI प्रयोग गरेर कुनै पनि भाषामा भिडियो र अडियोको भाषणलाई SRT उपशीर्षक फाइलमा ट्रान्सक्राइब गर्दछ।",
+ "presets.caption_video": "उपशीर्षकहरू सिर्जना गर्नुहोस् (Whisper)",
+ "presets.caption_video_hint": "Whisper प्रयोग गरी भिडियो र अडियोमा भएको भाषणलाई SRT उपशीर्षक फाइलमा ट्रान्सक्राइब गर्दछ।",
+ "presets.spoken_language": "बोलिने भाषा",
+ "presets.spoken_language.auto": "स्वचालित",
"presets.audio_codec": "अडियो कोडेक",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (लसलेस)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (भिडियो र अडियो)",
"engines.package.ffmpeg.description": "भिडियो र अडियो रूपान्तरण, भिडियो → GIF वा स्थिर छवि, भिडियोबाट ध्वनि र GIF → MP4 थप्छ।\nकेवल भिडियो र अडियोका लागि मात्र आवश्यक छ।",
"engines.package.whisper.name": "Whisper (AI उपशीर्षकहरू)",
- "engines.package.whisper.description": "कुनै पनि भाषामा भिडियो र अडियोमा भएको भाषणलाई SRT उपशीर्षक फाइलहरूमा ट्रान्सक्राइब गर्दछ।",
+ "engines.package.whisper.description": "भिडियो र अडियोमा भएको भाषणलाई SRT उपशीर्षक फाइलहरूमा ट्रान्सक्राइब गर्दछ। इन्टरनेट जडान बिना अफलाइन काम गर्दछ।",
"engines.package.calibre.name": "Calibre (Kindle र दुर्लभ इ-पुस्तक ढाँचाहरू)",
"engines.package.calibre.description": "Kindle का लागि MOBI र AZW3 सुरक्षित गर्दछ र दुर्लभ इ-पुस्तक ढाँचाहरू (LIT, LRF, PDB, CHM…) रूपान्तरण गर्दछ।\nEPUB, MOBI, AZW3, FB2 र कमिक्स यस बिना पनि पढ्न सकिन्छ।",
"engines.package.size": "डाउनलोड {0} · डिस्कमा {1}",
diff --git a/src/Filee.App/Assets/i18n/pl.json b/src/Filee.App/Assets/i18n/pl.json
index 37d59fb7..25ea6c35 100644
--- a/src/Filee.App/Assets/i18n/pl.json
+++ b/src/Filee.App/Assets/i18n/pl.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "Napisy: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD i SCC między sobą, zapisywane w UTF-8.\nKoreańskie pliki SMI i SRT w CP949 / EUC-KR są odczytywane poprawnie.",
"engine.ffmpeg.description": "Wideo i audio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC i inne.\nWyodrębnia też dźwięk i napisy, tworzy animacje GIF i APNG oraz zapisuje obrazy jako HEIC.",
- "engine.whisper.name": "Whisper (wbudowana SI)",
- "engine.whisper.description": "Transkrypcja mowy na tekst oparta na OpenAI Whisper. Automatycznie tworzy napisy do filmów i nagrań w dowolnym języku.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Transkrypcja mowy na tekst oparta na OpenAI Whisper. Automatycznie tworzy napisy SRT z mowy w plikach wideo i audio.",
"engine.pandoc.description": "Markdown i HTML ↔ ODT i RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter i inne ↔ Markdown, HTML, DOCX i ODT\nMarkdown i Org → slajdy PPTX",
"engine.ghostscript.description": "EPS, PostScript i starsze pliki Illustratora do PDF i obrazów; PDF do EPS i PS.",
"engine.tesseract.description": "Rozpoznaje tekst skanów i obrazów (OCR): przeszukiwalny PDF, DOCX, TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (najmniejszy, wolny)",
"presets.hardware_encoding": "Użyj akceleracji sprzętowej (karta graficzna)",
"presets.hardware_encoding_hint": "Koduje H.264, HEVC i AV1 na karcie graficznej.\nZnacznie szybciej i przy mniejszym zużyciu energii.\nNieco niższa jakość przy tym samym rozmiarze pliku.\nBez obsługiwanej karty (AV1 wymaga nowszej) wideo jest kodowane jak zwykle.",
- "presets.caption_video": "Utwórz napisy (Whisper SI)",
- "presets.caption_video_hint": "Transkrybuje mowę z filmów i dźwięku w dowolnym języku do pliku napisów SRT za pomocą Whisper SI.",
+ "presets.caption_video": "Generuj napisy (Whisper)",
+ "presets.caption_video_hint": "Transkrybuje mowę z filmów i nagrań audio do pliku napisów SRT za pomocą Whisper.",
+ "presets.spoken_language": "Język mówiony",
+ "presets.spoken_language.auto": "Automatycznie",
"presets.audio_codec": "Kodek audio",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (bezstratny)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (wideo i audio)",
"engines.package.ffmpeg.description": "Dodaje konwersję wideo i audio, wideo → GIF lub klatka, dźwięk z wideo i GIF → MP4.\nPotrzebny tylko do wideo i audio.",
"engines.package.whisper.name": "Whisper (napisy SI)",
- "engines.package.whisper.description": "Transkrybuje mowę z filmów i nagrań audio w dowolnym języku do plików napisów SRT.",
+ "engines.package.whisper.description": "Transkrybuje mowę z filmów i nagrań audio do plików napisów SRT. Działa offline bez połączenia z internetem.",
"engines.package.calibre.name": "Calibre (Kindle i rzadkie formaty e-booków)",
"engines.package.calibre.description": "Zapisuje MOBI i AZW3 dla Kindle i konwertuje rzadkie formaty e-booków (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 i komiksy są odczytywane bez niego.",
"engines.package.size": "Pobieranie {0} · {1} na dysku",
diff --git a/src/Filee.App/Assets/i18n/pt-BR.json b/src/Filee.App/Assets/i18n/pt-BR.json
index 40786338..e79f9c9a 100644
--- a/src/Filee.App/Assets/i18n/pt-BR.json
+++ b/src/Filee.App/Assets/i18n/pt-BR.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Legendas (mecanismo integrado)",
"engine.subtitle.description": "Legendas: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD e SCC entre si, salvas em UTF-8.\nArquivos SMI e SRT em coreano, em CP949 / EUC-KR, são lidos corretamente.",
"engine.ffmpeg.description": "Vídeo e áudio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC e mais.\nTambém extrai som e legendas, faz animações GIF e APNG e salva imagens como HEIC.",
- "engine.whisper.name": "Whisper (IA integrada)",
- "engine.whisper.description": "Transcrição de voz para texto com tecnologia OpenAI Whisper. Gera legendas automaticamente para vídeo e áudio em qualquer idioma.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Transcrição de voz para texto com tecnologia OpenAI Whisper. Gera legendas SRT automaticamente a partir da fala em vídeo e áudio.",
"engine.pandoc.description": "Markdown e HTML ↔ ODT e RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter e mais ↔ Markdown, HTML, DOCX e ODT\nMarkdown e Org → slides PPTX",
"engine.ghostscript.description": "EPS, PostScript e arquivos antigos do Illustrator para PDF e imagens; PDF para EPS e PS.",
"engine.tesseract.description": "Reconhece o texto de digitalizações e imagens (OCR): PDF pesquisável, DOCX, TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (menor, lento)",
"presets.hardware_encoding": "Usar aceleração de hardware (chip gráfico)",
"presets.hardware_encoding_hint": "Codifica H.264, HEVC e AV1 no chip gráfico.\nBem mais rápido e gasta menos energia.\nQualidade um pouco menor no mesmo tamanho de arquivo.\nSem um chip utilizável (o AV1 precisa de um recente), o vídeo é codificado como de costume.",
- "presets.caption_video": "Gerar legendas (Whisper IA)",
- "presets.caption_video_hint": "Transcreve a fala de vídeos e áudios em qualquer idioma para um arquivo de legendas SRT usando Whisper IA.",
+ "presets.caption_video": "Gerar legendas (Whisper)",
+ "presets.caption_video_hint": "Transcreve a fala de vídeos e áudios para um arquivo de legendas SRT usando Whisper.",
+ "presets.spoken_language": "Idioma falado",
+ "presets.spoken_language.auto": "Automático",
"presets.audio_codec": "Codec de áudio",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (sem perdas)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (vídeo e áudio)",
"engines.package.ffmpeg.description": "Adiciona conversão de vídeo e áudio, vídeo → GIF ou imagem parada, som de vídeos e GIF → MP4.\nSó é necessário para vídeo e áudio.",
"engines.package.whisper.name": "Whisper (legendas com IA)",
- "engines.package.whisper.description": "Transcreve a fala de vídeos e áudios em qualquer idioma para arquivos de legendas SRT.",
+ "engines.package.whisper.description": "Transcreve a fala de vídeos e áudios para arquivos de legendas SRT. Funciona offline sem conexão com a internet.",
"engines.package.calibre.name": "Calibre (Kindle e formatos raros de e-book)",
"engines.package.calibre.description": "Salva MOBI e AZW3 para Kindle e converte formatos raros de e-book (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 e quadrinhos são lidos sem ele.",
"engines.package.size": "Download de {0} · {1} em disco",
diff --git a/src/Filee.App/Assets/i18n/pt-PT.json b/src/Filee.App/Assets/i18n/pt-PT.json
index 7f2cfca8..9a1ed31c 100644
--- a/src/Filee.App/Assets/i18n/pt-PT.json
+++ b/src/Filee.App/Assets/i18n/pt-PT.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Legendas (motor integrado)",
"engine.subtitle.description": "Converte legendas entre SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD e SCC, guardadas em UTF-8.\nLê corretamente ficheiros SMI e SRT coreanos em CP949 / EUC-KR.",
"engine.ffmpeg.description": "Vídeo e áudio: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC e outros.\nTambém extrai som e legendas, cria animações GIF e APNG e guarda imagens em HEIC.",
- "engine.whisper.name": "Whisper (IA integrada)",
- "engine.whisper.description": "Transcrição de voz para texto com tecnologia OpenAI Whisper. Gera legendas automaticamente para vídeo e áudio em qualquer idioma.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Transcrição de voz para texto com tecnologia OpenAI Whisper. Gera legendas SRT automaticamente a partir da fala em vídeo e áudio.",
"engine.pandoc.description": "Markdown e HTML ↔ ODT e RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter e outros ↔ Markdown, HTML, DOCX e ODT\nMarkdown e Org → diapositivos PPTX",
"engine.ghostscript.description": "EPS, PostScript e ficheiros Illustrator antigos para PDF e imagens; PDF para EPS e PS.",
"engine.tesseract.description": "Reconhece o texto de digitalizações e imagens (OCR): PDF pesquisável, DOCX e TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (menor tamanho, lento)",
"presets.hardware_encoding": "Utilizar aceleração por hardware (chip gráfico)",
"presets.hardware_encoding_hint": "Codifica H.264, HEVC e AV1 no chip gráfico.\nMuito mais rápido e com menor consumo de energia.\nQualidade ligeiramente inferior para o mesmo tamanho de ficheiro.\nSem um chip compatível (o AV1 exige um chip recente), o vídeo é codificado da forma habitual.",
- "presets.caption_video": "Gerar legendas (Whisper IA)",
- "presets.caption_video_hint": "Transcreve a fala de vídeos e áudios em qualquer idioma para um ficheiro de legendas SRT usando Whisper IA.",
+ "presets.caption_video": "Gerar legendas (Whisper)",
+ "presets.caption_video_hint": "Transcreve a fala de vídeos e áudios para um ficheiro de legendas SRT usando Whisper.",
+ "presets.spoken_language": "Idioma falado",
+ "presets.spoken_language.auto": "Automático",
"presets.audio_codec": "Codec de áudio",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (sem perdas)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (vídeo e áudio)",
"engines.package.ffmpeg.description": "Adiciona conversão de vídeo e áudio, vídeo → GIF ou imagem fixa, extração de som de vídeos e GIF → MP4.\nSó é necessário para vídeo e áudio.",
"engines.package.whisper.name": "Whisper (legendas com IA)",
- "engines.package.whisper.description": "Transcreve a fala de vídeos e áudios em qualquer idioma para ficheiros de legendas SRT.",
+ "engines.package.whisper.description": "Transcreve a fala de vídeos e áudios para ficheiros de legendas SRT. Funciona offline sem ligação à Internet.",
"engines.package.calibre.name": "Calibre (Kindle e formatos raros de livros digitais)",
"engines.package.calibre.description": "Guarda em MOBI e AZW3 para Kindle e converte formatos raros de livros digitais (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 e banda desenhada são lidos sem ele.",
"engines.package.size": "Transferência de {0} · {1} no disco",
diff --git a/src/Filee.App/Assets/i18n/ru.json b/src/Filee.App/Assets/i18n/ru.json
index f87071b8..ae8d5882 100644
--- a/src/Filee.App/Assets/i18n/ru.json
+++ b/src/Filee.App/Assets/i18n/ru.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "Субтитры: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD и SCC друг в друга, с сохранением в UTF-8.\nКорейские SMI и SRT в CP949 / EUC-KR читаются правильно.",
"engine.ffmpeg.description": "Видео и аудио: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC и другие.\nА ещё достаёт звук и субтитры, делает анимации GIF и APNG и сохраняет картинки в HEIC.",
- "engine.whisper.name": "Whisper (встроенный ИИ)",
- "engine.whisper.description": "Распознавание речи на базе OpenAI Whisper. Автоматически создает субтитры для видео и аудио на любом языке.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "Распознавание речи на базе OpenAI Whisper. Автоматически создает субтитры SRT из речи в видео и аудио.",
"engine.pandoc.description": "Markdown и HTML ↔ ODT и RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter и другие ↔ Markdown, HTML, DOCX и ODT\nMarkdown и Org → слайды PPTX",
"engine.ghostscript.description": "EPS, PostScript и старые файлы Illustrator — в PDF и картинки; PDF — в EPS и PS.",
"engine.tesseract.description": "Распознаёт текст сканов и изображений (OCR): PDF с поиском, DOCX, TXT.",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1 (ещё меньше, медленно)",
"presets.hardware_encoding": "Аппаратное ускорение (видеочип)",
"presets.hardware_encoding_hint": "Кодирует H.264, HEVC и AV1 на видеочипе.\nНамного быстрее и тратит меньше энергии.\nКачество чуть ниже при том же размере файла.\nЕсли подходящего чипа нет (для AV1 нужен современный), видео кодируется как обычно.",
- "presets.caption_video": "Создать субтитры (Whisper ИИ)",
- "presets.caption_video_hint": "Преобразует речь из видео и аудио на любом языке в файл субтитров SRT с помощью Whisper ИИ.",
+ "presets.caption_video": "Создать субтитры (Whisper)",
+ "presets.caption_video_hint": "Преобразует речь из видео и аудио в файл субтитров SRT с помощью Whisper.",
+ "presets.spoken_language": "Язык речи",
+ "presets.spoken_language.auto": "Авто",
"presets.audio_codec": "Аудиокодек",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (без потерь)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg (видео и аудио)",
"engines.package.ffmpeg.description": "Добавляет конвертацию видео и аудио, видео → GIF или стоп-кадр, звук из видео и GIF → MP4.\nНужен только для видео и аудио.",
"engines.package.whisper.name": "Whisper (ИИ-субтитры)",
- "engines.package.whisper.description": "Преобразует речь из видео и аудио на любом языке в файлы субтитров SRT.",
+ "engines.package.whisper.description": "Преобразует речь из видео и аудио в файлы субтитров SRT. Работает автономно без подключения к Интернету.",
"engines.package.calibre.name": "Calibre (Kindle и редкие форматы книг)",
"engines.package.calibre.description": "Сохраняет MOBI и AZW3 для Kindle и конвертирует редкие форматы электронных книг (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 и комиксы читаются и без него.",
"engines.package.size": "Загрузка: {0} · на диске: {1}",
diff --git a/src/Filee.App/Assets/i18n/th.json b/src/Filee.App/Assets/i18n/th.json
index 2dc3e6c8..b1915d70 100644
--- a/src/Filee.App/Assets/i18n/th.json
+++ b/src/Filee.App/Assets/i18n/th.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "คำบรรยาย: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD และ SCC สลับกันได้ บันทึกเป็น UTF-8\nอ่านไฟล์ SMI และ SRT ภาษาเกาหลีในรหัส CP949 / EUC-KR ได้ถูกต้อง",
"engine.ffmpeg.description": "วิดีโอและเสียง: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC และอื่นๆ\nรวมถึงแยกเสียงและคำบรรยาย สร้างภาพเคลื่อนไหว GIF และ APNG และบันทึกภาพเป็น HEIC",
- "engine.whisper.name": "Whisper (AI ในตัว)",
- "engine.whisper.description": "การถอดเสียงเป็นข้อความขับเคลื่อนโดย OpenAI Whisper สร้างคำบรรยายสำหรับวิดีโอและเสียงในภาษาใดก็ได้โดยอัตโนมัติ",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "การถอดเสียงเป็นข้อความขับเคลื่อนโดย OpenAI Whisper สร้างคำบรรยาย SRT จากคำพูดในวิดีโอและเสียงโดยอัตโนมัติ",
"engine.pandoc.description": "Markdown และ HTML ↔ ODT และ RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter และอื่นๆ ↔ Markdown, HTML, DOCX และ ODT\nMarkdown และ Org → สไลด์ PPTX",
"engine.ghostscript.description": "EPS, PostScript และไฟล์ Illustrator รุ่นเก่าเป็น PDF และรูปภาพ แปลง PDF เป็น EPS และ PS",
"engine.tesseract.description": "อ่านข้อความจากภาพสแกนและรูปภาพ (OCR): PDF ที่ค้นหาได้, DOCX, TXT",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (ขนาดเล็กที่สุด, ช้า)",
"presets.hardware_encoding": "ใช้การเร่งความเร็วด้วยฮาร์ดแวร์ (ชิปกราฟิก)",
"presets.hardware_encoding_hint": "เข้ารหัส H.264, HEVC และ AV1 บนชิปกราฟิก\nเร็วกว่ามากและประหยัดพลังงาน\nคุณภาพอาจลดลงเล็กน้อยเมื่อเทียบกับขนาดไฟล์เดียวกัน\nหากไม่มีชิปที่รองรับ (AV1 ต้องใช้ชิปรุ่นใหม่) วิดีโอจะเข้ารหัสตามปกติ",
- "presets.caption_video": "สร้างคำบรรยาย (Whisper AI)",
- "presets.caption_video_hint": "ถอดเสียงคำพูดในวิดีโอและเสียงในภาษาใดก็ได้เป็นไฟล์คำบรรยาย SRT โดยใช้ Whisper AI",
+ "presets.caption_video": "สร้างคำบรรยาย (Whisper)",
+ "presets.caption_video_hint": "ถอดเสียงคำพูดในวิดีโอและเสียงเป็นไฟล์คำบรรยาย SRT โดยใช้ Whisper",
+ "presets.spoken_language": "ภาษาพูด",
+ "presets.spoken_language.auto": "อัตโนมัติ",
"presets.audio_codec": "โคเดกเสียง",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (ไม่สูญเสียรายละเอียด)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (วิดีโอและเสียง)",
"engines.package.ffmpeg.description": "เพิ่มการแปลงวิดีโอและเสียง วิดีโอ → GIF หรือภาพนิ่ง แยกเสียงจากวิดีโอ และ GIF → MP4\n(จำเป็นเฉพาะสำหรับงานวิดีโอและเสียงเท่านั้น)",
"engines.package.whisper.name": "Whisper (คำบรรยาย AI)",
- "engines.package.whisper.description": "ถอดเสียงคำพูดในวิดีโอและเสียงในภาษาใดก็ได้เป็นไฟล์คำบรรยาย SRT",
+ "engines.package.whisper.description": "ถอดเสียงคำพูดในวิดีโอและเสียงเป็นไฟล์คำบรรยาย SRT ทำงานแบบออฟไลน์โดยไม่ต้องเชื่อมต่ออินเทอร์เน็ต",
"engines.package.calibre.name": "Calibre (Kindle และอีบุ๊กหายาก)",
"engines.package.calibre.description": "บันทึกเป็น MOBI และ AZW3 สำหรับ Kindle และแปลงฟอร์แมตอีบุ๊กหายาก (LIT, LRF, PDB, CHM…)\n(EPUB, MOBI, AZW3, FB2 และการ์ตูนสามารถอ่านได้โดยไม่ต้องติดตั้ง)",
"engines.package.size": "ดาวน์โหลด {0} · ขนาดบนดิสก์ {1}",
diff --git a/src/Filee.App/Assets/i18n/tr.json b/src/Filee.App/Assets/i18n/tr.json
index 613107e1..afaa7f8b 100644
--- a/src/Filee.App/Assets/i18n/tr.json
+++ b/src/Filee.App/Assets/i18n/tr.json
@@ -204,8 +204,8 @@
"engine.subtitle.name": "Altyazılar (yerleşik)",
"engine.subtitle.description": "Altyazılar: SRT, ASS/SSA, WebVTT, SAMI (SMI), LRC, TTML, MicroDVD ve SCC arasında dönüştürme; UTF-8 olarak kaydedilir.\nCP949 / EUC-KR kodlamalı Korece SMI ve SRT dosyalarını doğru okur.",
"engine.ffmpeg.description": "Video ve ses: MP4, MOV, MKV, WEBM, MP3, M4A, WAV, FLAC ve daha fazlası.\nSes ve altyazı da çıkarır; GIF ve APNG animasyonları oluşturur, görselleri HEIC olarak kaydeder.",
- "engine.whisper.name": "Whisper (dahili YZ)",
- "engine.whisper.description": "OpenAI Whisper destekli sesten metne transkripsiyon. Her dilde video ve ses için otomatik olarak altyazı oluşturur.",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "OpenAI Whisper destekli sesten metne transkripsiyon. Video ve sesteki konuşmalardan otomatik olarak SRT altyazıları oluşturur.",
"engine.pandoc.description": "Markdown ve HTML ↔ ODT ve RTF, DOCX → Markdown\nreStructuredText, LaTeX, Org, AsciiDoc, Typst, MediaWiki, DocBook, Jupyter ve daha fazlası ↔ Markdown, HTML, DOCX ve ODT\nMarkdown ve Org → PPTX slaytları",
"engine.ghostscript.description": "EPS, PostScript ve eski Illustrator dosyaları → PDF ve görseller; PDF → EPS ve PS.",
"engine.tesseract.description": "Tarama ve görsellerdeki metni tanır (OCR): aranabilir PDF, DOCX, TXT.",
@@ -834,8 +834,10 @@
"presets.video_codec.av1": "AV1 (en küçük, yavaş)",
"presets.hardware_encoding": "Donanım hızlandırması kullan (grafik işlemcisi)",
"presets.hardware_encoding_hint": "H.264, HEVC ve AV1'i grafik işlemcisinde kodlar.\nÇok daha hızlıdır ve daha az güç tüketir.\nAynı dosya boyutunda kalite biraz daha düşüktür.\nUygun işlemci yoksa (AV1 için yeni bir model gerekir) video normal şekilde kodlanır.",
- "presets.caption_video": "Altyazı oluştur (Whisper YZ)",
- "presets.caption_video_hint": "Whisper YZ kullanarak videolardaki ve seslerdeki konuşmaları herhangi bir dilde SRT altyazı dosyasına dönüştürür.",
+ "presets.caption_video": "Altyazı oluştur (Whisper)",
+ "presets.caption_video_hint": "Whisper kullanarak video ve sesteki konuşmaları bir SRT altyazı dosyasına dönüştürür.",
+ "presets.spoken_language": "Konuşulan dil",
+ "presets.spoken_language.auto": "Otomatik",
"presets.audio_codec": "Ses codec'i",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC (kayıpsız)",
@@ -959,7 +961,7 @@
"engines.package.ffmpeg.name": "FFmpeg (video ve ses)",
"engines.package.ffmpeg.description": "Video ve ses dönüştürme, video → GIF veya durağan görsel, videodan ses çıkarma ve GIF → MP4 ekler.\nYalnızca video ve ses için gereklidir.",
"engines.package.whisper.name": "Whisper (YZ Altyazı)",
- "engines.package.whisper.description": "Herhangi bir dilde video ve sesteki konuşmaları SRT altyazı dosyalarına dönüştürür.",
+ "engines.package.whisper.description": "Video ve sesteki konuşmaları SRT altyazı dosyalarına dönüştürür. İnternet bağlantısı olmadan çevrimdışı çalışır.",
"engines.package.calibre.name": "Calibre (Kindle ve nadir e-kitap biçimleri)",
"engines.package.calibre.description": "Kindle için MOBI ve AZW3 kaydeder; nadir e-kitap biçimlerini dönüştürür (LIT, LRF, PDB, CHM…).\nEPUB, MOBI, AZW3, FB2 ve çizgi romanlar bu motor olmadan okunur.",
"engines.package.size": "İndirme {0} · Diskte {1}",
diff --git a/src/Filee.App/Assets/i18n/zh-CN.json b/src/Filee.App/Assets/i18n/zh-CN.json
index 0748389a..ba5750af 100644
--- a/src/Filee.App/Assets/i18n/zh-CN.json
+++ b/src/Filee.App/Assets/i18n/zh-CN.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "SRT、ASS/SSA、WebVTT、SAMI(SMI)、LRC、TTML、MicroDVD、SCC 字幕互转,保存为 UTF-8。\n也能正确读取 CP949/EUC-KR 编码的韩文字幕。",
"engine.ffmpeg.description": "MP4、MOV、MKV、WEBM、MP3、M4A、WAV、FLAC 等视频和音频。\n还能提取声音和字幕、制作 GIF 和 APNG、把图片保存为 HEIC。",
- "engine.whisper.name": "Whisper (内置AI)",
- "engine.whisper.description": "基于 OpenAI Whisper 的语音转文本。自动为任何语言的视频和音频生成字幕。",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "基于 OpenAI Whisper 的语音转文本。自动将视频和音频中的语音生成为 SRT 字幕。",
"engine.pandoc.description": "Markdown 和 HTML ↔ ODT、RTF,DOCX → Markdown\nreStructuredText、LaTeX、Org、AsciiDoc、Typst、MediaWiki、DocBook、Jupyter 等 ↔ Markdown、HTML、DOCX、ODT\nMarkdown 和 Org → PPTX 幻灯片",
"engine.ghostscript.description": "EPS、PostScript 和旧版 Illustrator 文件转为 PDF 和图片;PDF 转为 EPS 和 PS。",
"engine.tesseract.description": "识别扫描件和图片中的文字(OCR):可搜索的 PDF、DOCX、TXT。",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1(最小,较慢)",
"presets.hardware_encoding": "使用硬件加速(显卡)",
"presets.hardware_encoding_hint": "用显卡编码 H.264、HEVC 和 AV1。\n速度快得多,也更省电。\n相同文件大小时画质略低。\n没有可用的显卡时(AV1 需要较新的显卡)照常编码。",
- "presets.caption_video": "生成字幕 (Whisper AI)",
- "presets.caption_video_hint": "使用 Whisper AI 将视频和音频中的语音转录为任意语言的 SRT 字幕文件。",
+ "presets.caption_video": "生成字幕 (Whisper)",
+ "presets.caption_video_hint": "使用 Whisper 将视频和音频中的语音转录为 SRT 字幕文件。",
+ "presets.spoken_language": "语音语言",
+ "presets.spoken_language.auto": "自动",
"presets.audio_codec": "音频编码",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC(无损)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg(视频和音频)",
"engines.package.ffmpeg.description": "增加视频和音频转换、视频 → GIF 或静态图片、提取声音以及 GIF → MP4。\n仅视频和音频转换需要它。",
"engines.package.whisper.name": "Whisper (AI字幕)",
- "engines.package.whisper.description": "将视频和音频中的语音转录为任意语言的 SRT 字幕文件。",
+ "engines.package.whisper.description": "将视频和音频中的语音转录为 SRT 字幕文件。无需互联网连接即可离线运行。",
"engines.package.calibre.name": "Calibre(Kindle 与少见电子书格式)",
"engines.package.calibre.description": "可保存为 Kindle 用的 MOBI 和 AZW3,并转换少见的电子书格式(LIT、LRF、PDB、CHM 等)。\nEPUB、MOBI、AZW3、FB2 和漫画无需它即可读取。",
"engines.package.size": "下载 {0} · 占用 {1}",
diff --git a/src/Filee.App/Assets/i18n/zh-TW.json b/src/Filee.App/Assets/i18n/zh-TW.json
index eb4e005c..0967d8ae 100644
--- a/src/Filee.App/Assets/i18n/zh-TW.json
+++ b/src/Filee.App/Assets/i18n/zh-TW.json
@@ -211,8 +211,8 @@
"engine.subtitle.name": "Subtitles (built-in)",
"engine.subtitle.description": "SRT、ASS/SSA、WebVTT、SAMI(SMI)、LRC、TTML、MicroDVD、SCC 字幕互轉,儲存為 UTF-8。\n也能正確讀取 CP949/EUC-KR 編碼的韓文字幕。",
"engine.ffmpeg.description": "MP4、MOV、MKV、WEBM、MP3、M4A、WAV、FLAC 等影片和音訊。\n還能擷取聲音和字幕、製作 GIF 和 APNG、把圖片儲存為 HEIC。",
- "engine.whisper.name": "Whisper (內建AI)",
- "engine.whisper.description": "以 OpenAI Whisper 驅動的語音轉文字。自動為任何語言的影片與音訊產生字幕。",
+ "engine.whisper.name": "Whisper",
+ "engine.whisper.description": "以 OpenAI Whisper 驅動的語音轉文字。自動將影片與音訊中的語音產生為 SRT 字幕。",
"engine.pandoc.description": "Markdown 和 HTML ↔ ODT、RTF,DOCX → Markdown\nreStructuredText、LaTeX、Org、AsciiDoc、Typst、MediaWiki、DocBook、Jupyter 等 ↔ Markdown、HTML、DOCX、ODT\nMarkdown 和 Org → PPTX 投影片",
"engine.ghostscript.description": "EPS、PostScript 和舊版 Illustrator 檔案轉為 PDF 和圖片;PDF 轉為 EPS 和 PS。",
"engine.tesseract.description": "辨識掃描檔和圖片中的文字(OCR):可搜尋的 PDF、DOCX、TXT。",
@@ -849,8 +849,10 @@
"presets.video_codec.av1": "AV1(最小,較慢)",
"presets.hardware_encoding": "使用硬體加速(顯示卡)",
"presets.hardware_encoding_hint": "用顯示卡編碼 H.264、HEVC 和 AV1。\n速度快得多,也更省電。\n相同檔案大小時畫質略低。\n沒有可用的顯示卡時(AV1 需要較新的顯示卡)照常編碼。",
- "presets.caption_video": "產生字幕 (Whisper AI)",
- "presets.caption_video_hint": "使用 Whisper AI 將影片與音訊中的語音轉錄為任意語言的 SRT 字幕檔。",
+ "presets.caption_video": "產生字幕 (Whisper)",
+ "presets.caption_video_hint": "使用 Whisper 將影片與音訊中的語音轉錄為 SRT 字幕檔。",
+ "presets.spoken_language": "語音語言",
+ "presets.spoken_language.auto": "自動",
"presets.audio_codec": "音訊編碼",
"presets.audio_codec.aac": "AAC",
"presets.audio_codec.alac": "ALAC(無損)",
@@ -976,7 +978,7 @@
"engines.package.ffmpeg.name": "FFmpeg(影片和音訊)",
"engines.package.ffmpeg.description": "增加影片和音訊轉換、影片 → GIF 或靜態圖片、擷取聲音以及 GIF → MP4。\n僅影片和音訊轉換需要它。",
"engines.package.whisper.name": "Whisper (AI字幕)",
- "engines.package.whisper.description": "將影片與音訊中的語音轉錄為任意語言的 SRT 字幕檔。",
+ "engines.package.whisper.description": "將影片與音訊中的語音轉錄為 SRT 字幕檔。無需網際網路連線即可離線執行。",
"engines.package.calibre.name": "Calibre(Kindle 與少見電子書格式)",
"engines.package.calibre.description": "可儲存為 Kindle 用的 MOBI 和 AZW3,並轉換少見的電子書格式(LIT、LRF、PDB、CHM 等)。\nEPUB、MOBI、AZW3、FB2 和漫畫無需它即可讀取。",
"engines.package.size": "下載 {0} · 佔用 {1}",
diff --git a/src/Filee.App/ViewModels/PresetEditorViewModel.cs b/src/Filee.App/ViewModels/PresetEditorViewModel.cs
index fe56cb04..b27c2dab 100644
--- a/src/Filee.App/ViewModels/PresetEditorViewModel.cs
+++ b/src/Filee.App/ViewModels/PresetEditorViewModel.cs
@@ -113,6 +113,13 @@ public sealed partial class PresetEditorViewModel : ObservableObject
// A speed set outside the editor (a hand-edited preset file) is offered too, instead of being lost.
AnimationSpeeds = [.. ImageOptions.AnimationSpeeds.Append(_edit.Image.PlaybackSpeed).Distinct().Order()
.Select(s => new Choice<double>(s, s == 1 ? loc["presets.animation_speed.original"] : SpeedLabel(s)))];
+ SpokenLanguageChoices =
+ [
+ new Choice<string>(WhisperLanguages.Auto, loc["presets.spoken_language.auto"]),
+ .. WhisperLanguages.All
+ .OrderBy(l => l.DisplayName, StringComparer.CurrentCulture)
+ .Select(l => new Choice<string>(l.Code, l.DisplayName))
+ ];
_name = string.IsNullOrWhiteSpace(_edit.Name) ? loc.DisplayName(_edit) : _edit.Name;
_target = Targets.FirstOrDefault(t => t.Value == _edit.TargetFormat) ?? Targets[1];
@@ -145,6 +152,8 @@ public sealed partial class PresetEditorViewModel : ObservableObject
_audioCodecValue = _edit.Media.AudioCodec;
_hardwareEncoding = _edit.Media.HardwareEncoding;
_caption = _edit.Media.Caption;
+ _spokenLanguage = SpokenLanguageChoices.FirstOrDefault(l => string.Equals(l.Value, _edit.Media.SpokenLanguage, StringComparison.OrdinalIgnoreCase))
+ ?? SpokenLanguageChoices[0];
_archiveLevel = ArchiveLevels.First(l => l.Value == _edit.Archive.Level);
_combineIntoOne = _edit.Archive.CombineIntoOne;
_saveEveryFrame = _edit.Media.SaveEveryFrame;
@@ -218,6 +227,8 @@ public sealed partial class PresetEditorViewModel : ObservableObject
/// <summary>Languages Tesseract reads (PdfOptions.OcrLanguage), English first.</summary>
public IReadOnlyList<Choice<string>> OcrLanguageChoices { get; }
+ /// <summary>The spoken languages Whisper recognizes (MediaOptions.SpokenLanguage), Auto first.</summary>
+ public IReadOnlyList<Choice<string>> SpokenLanguageChoices { get; }
/// <summary>What "Recognize text" needs: Tesseract, or on a Mac Apple Vision (Tesseract only for other languages).</summary>
public string OcrHint { get; }
@@ -513,6 +524,8 @@ public sealed partial class PresetEditorViewModel : ObservableObject
[ObservableProperty] private bool _hardwareEncoding;
/// <summary>Burn subtitles from speech recognized by Whisper AI (MediaOptions.Caption).</summary>
[ObservableProperty] private bool _caption;
+ /// <summary>Language spoken in the audio for Whisper transcription (MediaOptions.SpokenLanguage).</summary>
+ [ObservableProperty] private Choice<string> _spokenLanguage;
[ObservableProperty] private Choice<ArchiveLevel> _archiveLevel;
[ObservableProperty] private bool _combineIntoOne;
[ObservableProperty] private bool _saveEveryFrame;
@@ -804,6 +817,7 @@ public sealed partial class PresetEditorViewModel : ObservableObject
media.AudioCodec = MediaCodecs.Effective(TargetId, _audioCodecValue);
media.HardwareEncoding = HardwareEncoding;
media.Caption = ShowCaption && Caption;
+ media.SpokenLanguage = SpokenLanguage.Value;
// Only where the option is shown: a box ticked for PNG and left behind by another target saves nothing.
media.SaveEveryFrame = ShowSaveEveryFrame && SaveEveryFrame;
media.FrameInterval = media.SaveEveryFrame ? Math.Clamp(FrameInterval, 1, 1000) : 1;
diff --git a/src/Filee.App/Views/PresetEditorView.axaml b/src/Filee.App/Views/PresetEditorView.axaml
index ceff0149..fd2a6e74 100644
--- a/src/Filee.App/Views/PresetEditorView.axaml
+++ b/src/Filee.App/Views/PresetEditorView.axaml
@@ -295,6 +295,19 @@
<StackPanel Spacing="2" IsVisible="{Binding ShowCaption}">
<CheckBox Content="{DynamicResource presets.caption_video}" IsChecked="{Binding Caption}" />
<TextBlock Classes="caption" TextWrapping="Wrap" Margin="28,0,0,0" Text="{DynamicResource presets.caption_video_hint}" />
+ <Grid ColumnDefinitions="*,12,*" Margin="28,6,0,0" IsVisible="{Binding Caption}">
+ <StackPanel>
+ <TextBlock Classes="label" Text="{DynamicResource presets.spoken_language}" />
+ <ComboBox ItemsSource="{Binding SpokenLanguageChoices}" SelectedItem="{Binding SpokenLanguage}" HorizontalAlignment="Stretch"
+ HorizontalContentAlignment="Stretch" MaxDropDownHeight="420" AutomationProperties.Name="{DynamicResource presets.spoken_language}">
+ <ComboBox.ItemTemplate>
+ <DataTemplate x:DataType="vm:IChoice">
+ <TextBlock Text="{Binding Label}" TextTrimming="CharacterEllipsis" VerticalAlignment="Center" />
+ </DataTemplate>
+ </ComboBox.ItemTemplate>
+ </ComboBox>
+ </StackPanel>
+ </Grid>
</StackPanel>
</StackPanel>
</Border>
diff --git a/src/Filee.Core/Presets/BuiltInData.cs b/src/Filee.Core/Presets/BuiltInData.cs
index 6328320a..d92aa7d8 100644
--- a/src/Filee.Core/Presets/BuiltInData.cs
+++ b/src/Filee.Core/Presets/BuiltInData.cs
@@ -674,7 +674,7 @@ public static class BuiltInData
{
Id = "video", NameKey = "profile.video",
Extensions = ExtensionsOf(FormatCategory.Video),
- PresetIds = OperatingSystem.IsWindows() ? ["to-mp4", "mp4-720", "mp4-hevc", "to-webm", "to-mov", "to-gif", "to-mp3", "extract-subtitles", "caption-video", "to-mkv", "to-avi"] : ["to-mp4", "mp4-720", "mp4-hevc", "to-webm", "to-mov", "to-gif", "to-mp3", "extract-subtitles", "to-mkv", "to-avi"],
+ PresetIds = ["to-mp4", "mp4-720", "mp4-hevc", "to-webm", "to-mov", "to-gif", "to-mp3", "extract-subtitles", "caption-video", "to-mkv", "to-avi"],
// Every frame as pictures is on no front (a long video gives thousands of files): behind a flip, a drop that
// misses its slice doesn't start it. Live / Motion Photos of a clip are there too, and "Cut a clip" first
// (in place of FLAC, which stays in the library).
@@ -685,7 +685,7 @@ public static class BuiltInData
{
Id = "audio", NameKey = "profile.audio",
Extensions = ExtensionsOf(FormatCategory.Audio),
- PresetIds = OperatingSystem.IsWindows() ? ["to-mp3", "mp3-128", "to-m4a", "to-wav", "to-flac", "to-ogg", "to-opus", "to-aac", "caption-video"] : ["to-mp3", "mp3-128", "to-m4a", "to-wav", "to-flac", "to-ogg", "to-opus", "to-aac"],
+ PresetIds = ["to-mp3", "mp3-128", "to-m4a", "to-wav", "to-flac", "to-ogg", "to-opus", "to-aac", "caption-video"],
BackPresetIds = ["to-alac", "compress-audio", "merge-audio", "remove-metadata", "zip-all"],
},
new()
diff --git a/src/Filee.Core/Presets/WhisperLanguages.cs b/src/Filee.Core/Presets/WhisperLanguages.cs
new file mode 100644
index 00000000..99191e8a
--- /dev/null
+++ b/src/Filee.Core/Presets/WhisperLanguages.cs
@@ -0,0 +1,131 @@
+// The spoken languages recognized by OpenAI Whisper (whisper.cpp).
+// Code is the ISO-639 / whisper language identifier; Name is the English language name.
+
+using System.Globalization;
+
+namespace Filee.Core.Presets;
+
+/// <summary>A spoken language recognized by Whisper AI.</summary>
+/// <param name="Code">Language code passed to whisper.cpp (<c>-l &lt;code&gt;</c>).</param>
+/// <param name="Name">The English language name from whisper.cpp.</param>
+public sealed record WhisperLanguage(string Code, string Name)
+{
+ /// <summary>Title-cased display name (e.g. "English", "Hindi", "French").</summary>
+ public string DisplayName => CultureInfo.InvariantCulture.TextInfo.ToTitleCase(Name);
+}
+
+/// <summary>The spoken languages supported by Whisper AI.</summary>
+public static class WhisperLanguages
+{
+ /// <summary>Auto-detect the spoken language from audio (whisper.cpp default).</summary>
+ public const string Auto = "auto";
+
+ /// <summary>All languages known to whisper.cpp.</summary>
+ public static readonly IReadOnlyList<WhisperLanguage> All =
+ [
+ new("en", "english"),
+ new("zh", "chinese"),
+ new("de", "german"),
+ new("es", "spanish"),
+ new("ru", "russian"),
+ new("ko", "korean"),
+ new("fr", "french"),
+ new("ja", "japanese"),
+ new("pt", "portuguese"),
+ new("tr", "turkish"),
+ new("pl", "polish"),
+ new("ca", "catalan"),
+ new("nl", "dutch"),
+ new("ar", "arabic"),
+ new("sv", "swedish"),
+ new("it", "italian"),
+ new("id", "indonesian"),
+ new("hi", "hindi"),
+ new("fi", "finnish"),
+ new("vi", "vietnamese"),
+ new("he", "hebrew"),
+ new("uk", "ukrainian"),
+ new("el", "greek"),
+ new("ms", "malay"),
+ new("cs", "czech"),
+ new("ro", "romanian"),
+ new("da", "danish"),
+ new("hu", "hungarian"),
+ new("ta", "tamil"),
+ new("no", "norwegian"),
+ new("th", "thai"),
+ new("ur", "urdu"),
+ new("hr", "croatian"),
+ new("bg", "bulgarian"),
+ new("lt", "lithuanian"),
+ new("la", "latin"),
+ new("mi", "maori"),
+ new("ml", "malayalam"),
+ new("cy", "welsh"),
+ new("sk", "slovak"),
+ new("te", "telugu"),
+ new("fa", "persian"),
+ new("lv", "latvian"),
+ new("bn", "bengali"),
+ new("sr", "serbian"),
+ new("az", "azerbaijani"),
+ new("sl", "slovenian"),
+ new("kn", "kannada"),
+ new("et", "estonian"),
+ new("mk", "macedonian"),
+ new("br", "breton"),
+ new("eu", "basque"),
+ new("is", "icelandic"),
+ new("hy", "armenian"),
+ new("ne", "nepali"),
+ new("mn", "mongolian"),
+ new("bs", "bosnian"),
+ new("kk", "kazakh"),
+ new("sq", "albanian"),
+ new("sw", "swahili"),
+ new("gl", "galician"),
+ new("mr", "marathi"),
+ new("pa", "punjabi"),
+ new("si", "sinhala"),
+ new("km", "khmer"),
+ new("sn", "shona"),
+ new("yo", "yoruba"),
+ new("so", "somali"),
+ new("af", "afrikaans"),
+ new("oc", "occitan"),
+ new("ka", "georgian"),
+ new("be", "belarusian"),
+ new("tg", "tajik"),
+ new("sd", "sindhi"),
+ new("gu", "gujarati"),
+ new("am", "amharic"),
+ new("yi", "yiddish"),
+ new("lo", "lao"),
+ new("uz", "uzbek"),
+ new("fo", "faroese"),
+ new("ht", "haitian creole"),
+ new("ps", "pashto"),
+ new("tk", "turkmen"),
+ new("nn", "nynorsk"),
+ new("mt", "maltese"),
+ new("sa", "sanskrit"),
+ new("lb", "luxembourgish"),
+ new("my", "myanmar"),
+ new("bo", "tibetan"),
+ new("tl", "tagalog"),
+ new("mg", "malagasy"),
+ new("as", "assamese"),
+ new("tt", "tatar"),
+ new("haw", "hawaiian"),
+ new("ln", "lingala"),
+ new("ha", "hausa"),
+ new("ba", "bashkir"),
+ new("jw", "javanese"),
+ new("su", "sundanese"),
+ new("yue", "cantonese"),
+ ];
+
+ /// <summary>Finds a language by its code (case-insensitive).</summary>
+ public static WhisperLanguage? Find(string code) =>
+ All.FirstOrDefault(l => string.Equals(l.Code, code, StringComparison.OrdinalIgnoreCase));
+}
diff --git a/src/Filee.Core/Settings/UserDataStore.cs b/src/Filee.Core/Settings/UserDataStore.cs
index 79c0c143..592f93da 100644
--- a/src/Filee.Core/Settings/UserDataStore.cs
+++ b/src/Filee.Core/Settings/UserDataStore.cs
@@ -962,11 +962,8 @@ internal static class SettingsMigrations
presets.Insert(at < 0 ? presets.Count : at + 1, caption);
changed = true;
}
- if (OperatingSystem.IsWindows())
- {
- changed |= Offer(presets, profiles, "video", caption.Id, "extract-subtitles");
- changed |= Offer(presets, profiles, "audio", caption.Id, "to-aac");
- }
+ changed |= Offer(presets, profiles, "video", caption.Id, "extract-subtitles");
+ changed |= Offer(presets, profiles, "audio", caption.Id, "to-aac");
return changed;
}
diff --git a/src/Filee.Engines/Media/WhisperConverter.cs b/src/Filee.Engines/Media/WhisperConverter.cs
index c272e814..549e65b9 100644
--- a/src/Filee.Engines/Media/WhisperConverter.cs
+++ b/src/Filee.Engines/Media/WhisperConverter.cs
@@ -1,6 +1,8 @@
// Transcribes speech in video and audio using OpenAI Whisper (whisper.cpp) into SRT subtitles.
+using System.Globalization;
using System.Text;
+using System.Text.RegularExpressions;
using Filee.Core.Conversion;
using Filee.Core.Formats;
using Filee.Engines.Infrastructure;
@@ -10,11 +12,13 @@ using Microsoft.Extensions.Logging.Abstractions;
namespace Filee.Engines.Media;
/// <summary>
-/// AI-powered speech transcription engine powered by OpenAI Whisper.
+/// Speech transcription engine powered by OpenAI Whisper.
/// Transcribes speech in video and audio files into SRT subtitles.
/// </summary>
-public sealed class WhisperConverter : IConverter
+public sealed partial class WhisperConverter : IConverter
{
+ private static readonly TimeSpan StallTimeout = TimeSpan.FromMinutes(5);
+
private readonly ILogger _logger;
public WhisperConverter(ILogger<WhisperConverter>? logger = null)
@@ -23,7 +27,7 @@ public sealed class WhisperConverter : IConverter
}
public string Id => "whisper";
- public string DisplayName => "Whisper (AI Captions)";
+ public string DisplayName => "Whisper";
public int MaxParallelism => 1;
public IReadOnlyList<ConversionEdge> Edges { get; } = BuildEdges();
@@ -133,23 +137,24 @@ public sealed class WhisperConverter : IConverter
var ffmpeg = ffmpegTools.Value.Ffmpeg;
cancellationToken.ThrowIfCancellationRequested();
- progress?.Report(0.05);
+ progress?.Report(0.02);
// 1. Extract 16kHz mono WAV for Whisper inference (works for both video and audio files)
var audioWav = Path.Combine(step.WorkDirectory, $"whisper_audio_{Guid.NewGuid():N}.wav");
var extractArgs = new[]
{
- "-y", "-nostdin", "-hide_banner", "-v", "error",
+ "-hide_banner", "-nostdin", "-nostats", "-v", "error", "-y",
"-i", step.InputPath,
"-vn", "-ar", "16000", "-ac", "1",
+ "-progress", "pipe:1",
audioWav
};
- var extractResult = await ProcessRunner.RunAsync(ffmpeg, extractArgs, TimeSpan.FromMinutes(10), cancellationToken);
+ var extractResult = await FfmpegRunner.RunAsync(ffmpeg, extractArgs, null, cancellationToken, StallTimeout);
if (extractResult.ExitCode != 0 || !File.Exists(audioWav))
throw new InvalidOperationException($"FFmpeg failed to extract audio: {extractResult.StandardError}");
- progress?.Report(0.20);
+ progress?.Report(0.10);
cancellationToken.ThrowIfCancellationRequested();
// 2. Run Whisper CLI transcription (auto-detect language or preset's SpokenLanguage, srt output)
@@ -158,6 +163,7 @@ public sealed class WhisperConverter : IConverter
? "auto"
: step.Preset.Media.SpokenLanguage.Trim();
+ var threads = Math.Clamp(Environment.ProcessorCount, 1, 8).ToString(CultureInfo.InvariantCulture);
var whisperArgs = new[]
{
"-m", modelPath,
@@ -165,11 +171,19 @@ public sealed class WhisperConverter : IConverter
"-osrt",
"-of", outPrefix,
"-l", lang,
- "-t", "4",
- "-sow"
+ "-t", threads,
+ "-sow",
+ "-pp"
};
- var whisperResult = await ProcessRunner.RunAsync(whisperCli, whisperArgs, TimeSpan.FromMinutes(30), cancellationToken);
+ var whisperResult = await ProcessRunner.RunAsync(
+ whisperCli,
+ whisperArgs,
+ Timeout.InfiniteTimeSpan,
+ cancellationToken,
+ onOutput: line => ReportWhisperProgress(line, progress),
+ stallTimeout: StallTimeout);
+
var srtPath = outPrefix + ".srt";
if (!File.Exists(srtPath) || whisperResult.ExitCode != 0)
@@ -177,7 +191,6 @@ public sealed class WhisperConverter : IConverter
var srtContent = await File.ReadAllTextAsync(srtPath, cancellationToken);
- progress?.Report(0.85);
cancellationToken.ThrowIfCancellationRequested();
// 3. Produce SRT output
@@ -189,4 +202,16 @@ public sealed class WhisperConverter : IConverter
progress?.Report(1.0);
return [srtOutput];
}
+
+ private static void ReportWhisperProgress(string line, IProgress<double>? progress)
+ {
+ if (progress is not null && ProgressPercent().Match(line) is { Success: true } match
+ && int.TryParse(match.Groups[1].Value, NumberStyles.None, CultureInfo.InvariantCulture, out var percent))
+ {
+ progress.Report(0.10 + (Math.Clamp(percent, 0, 100) / 100.0 * 0.88));
+ }
+ }
+
+ [GeneratedRegex(@"progress\s*=\s*(\d{1,3})%")]
+ private static partial Regex ProgressPercent();
}
diff --git a/tests/Filee.Core.Tests/CaptionRouteTests.cs b/tests/Filee.Core.Tests/CaptionRouteTests.cs
index 316c9dbf..e102b6c9 100644
--- a/tests/Filee.Core.Tests/CaptionRouteTests.cs
+++ b/tests/Filee.Core.Tests/CaptionRouteTests.cs
@@ -93,16 +93,8 @@ public class CaptionRouteTests
Assert.False(SettingsMigrations.ApplyToLibrary(56, presets, profiles)); // once only
Assert.Contains(presets, p => p.Id == "caption-video");
- if (OperatingSystem.IsWindows())
- {
- Assert.Contains("caption-video", video.PresetIds);
- Assert.Contains("caption-video", audio.PresetIds);
- }
- else
- {
- Assert.DoesNotContain("caption-video", video.PresetIds);
- Assert.DoesNotContain("caption-video", audio.PresetIds);
- }
+ Assert.Contains("caption-video", video.PresetIds);
+ Assert.Contains("caption-video", audio.PresetIds);
}
[Fact]
diff --git a/tests/Filee.Engines.Tests/WhisperTests.cs b/tests/Filee.Engines.Tests/WhisperTests.cs
index 93747dec..7d9ad726 100644
--- a/tests/Filee.Engines.Tests/WhisperTests.cs
+++ b/tests/Filee.Engines.Tests/WhisperTests.cs
@@ -11,7 +11,7 @@ public class WhisperTests
var converter = new WhisperConverter();
Assert.Equal("whisper", converter.Id);
- Assert.Equal("Whisper (AI Captions)", converter.DisplayName);
+ Assert.Equal("Whisper", converter.DisplayName);
Assert.NotEmpty(converter.Edges);
// Every edge must produce srt directly and require the Caption flag