UPDF Converter
UPDF Converter for Windows and Mac is an easy-to-use PDF Converter with OCR. It allows you to convert PDF documents to other formats or extensions without losing formats and layouts. It supports converting a single PDF or dozens of PDFs in batch with one click. UPDF Converter is a powerful all-in-one converter for your PDF files.
Key features:
1. Supported Conversion Formats:
Convert PDF to fully editable Microsoft Office Word, Excel, PowerPoint and other formats, such as Image (PNG, JPEG, BMP, GIF, TIFF), HTML, XML, CSV, Text, PDF/A. It is an offline converter! It is safe and faster!
2. Convert Scanned Documents with OCR:
UPDF supports converting scanned PDF to editable and searchable text. It supports recognizing over 15+ languages including English, French, German, Italian, Portuguese, Russian, Spanish, Catalan, Danish, Dutch, Norwegian, Polish, Romanian, Swedish, Slovenian, and Turkish.
Learn more
mT5
Multilingual T5 (mT5) is a massively multilingual pretrained text-to-text transformer model, trained following a similar recipe as T5. This repo can be used to reproduce the experiments in the mT5 paper.
mT5 is pretrained on the mC4 corpus, covering 101 languages:
Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, and more.
Learn more
MAI-Voice-2
MAI-Voice-2 is Microsoft AI’s most expressive and natural-sounding text-to-speech model to date, built for production voice experiences where fidelity, language coverage, speaker consistency, and emotional range directly shape the user experience. It is designed for assistants, customer support, audiobooks, accessibility experiences, games, podcasts, courses, simulations, and creator workflows where voice quality must sound natural, fluid, and trustworthy. It expands from English-only support to 15 languages while maintaining naturalness and expressiveness, with support for English, Italian, French, German, Hindi, Spanish, Portuguese, Korean, Chinese, Turkish, Russian, Thai, Dutch, Romanian, and Hungarian. MAI-Voice-2 offers granular emotion control through tags such as sad, whispered, and excited, along with role-based expressive speech for experiences like motivational trainers, sports commentators, or character voices.
Learn more