view post Post 3274 Whisper-WebUI Premium - Ultra Fast and High Accuracy Speech to Text Transcripton App for All Languages - Windows, RunPod, Massed Compute 1-Click Installers - Supporting RTX 1000 to 5000 series Latest installer zip file : https://www.patreon.com/posts/145395299New FeaturesPassword protected version, password is just 1 : WhisperWeb_UI_v1_password_is_1.zipIt has better interface, more features, default settings set for maximum accuracyIt will show transcription realtime both on Gradio interface and also on CMDIt will show better status and output at the cmd like starting time, starting file, etcIt will save every generated transcription properly with same name as input file name with proper name sanitizationAfter deep scan of the entire pipeline, default parameters are set for maximum accuracy and quality1-Click installers for Windows local PC, RunPod (Linux-Cloud) and Massed Compute (Linux-Cloud)The app the installers are made for RTX 1000 series to RTX 5000 series with pre-compiled librariesWe install with Torch 2.8, CUDA 12.9, latest Flash Attention, Sage Attention, xFormers - all precompiledAs low as 6 GB VRAM GPUs can useOpenAI Whisper Supported Models:tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2, large-v3, large, large-v3-turbo, turboDistil-Whisper Supported Models (Faster-Whisper & Insanely-Fast-Whisper):distil-large-v2, distil-large-v3, distil-medium.en, distil-small.en100 languages are supported See translation 🔥 5 5 👀 2 2 ❤️ 2 2 👍 2 2 🚀 1 1 🤗 1 1 😎 1 1 ➕ 1 1 🧠 1 1 🤝 1 1 🤯 1 1 😔 1 1 + Reply
Running MCP Featured 184 Karpathy Llm Council 🏢 184 Ask a question to get a consensus answer from multiple models