TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #15385 · Jan 2

#python#deep_learning#inference#openai#quantization#speech_recognition#speech_to_text#transformer#whisper Faster-Whisper is a fast version of OpenAI's Whisper that transcribes audio up to 4x quicker with the same accuracy, using less memory on CPU or GPU—benchmarks show it beats original Whisper (e.g., 1m03s vs 2m23s for 13-min audio on GPU). Install via `pip install faster-whisper`, no FFmpeg needed, and use simple Python code like `WhisperModel("large-v3").transcribe("audio.mp3")` for segments with timestamps. You benefit by getting quick, efficient speech-to-text for real-time apps, saving time and resources on long files or batches. https://github.com/SYSTRAN/faster-whisper

Results

1 similar post found

Search: #rigidity

当前筛选 #rigidity清除筛选
Architectural Shovel / Любовь Дмитриева

@arch_shovel · Post #663 · 09/07/2022, 08:31 PM

C U R V E S / Under Magnitude by Marc Fornes / THEVERYMANY The strength of #undermagnitude is achieved by 'Intensive Curvature,' which is the maximization of double #curvature across the project while constraining maximum radii. The result is a #structure that has much tighter curvature with constant change of direction, and results in more structurally performance. 'Intensive Curvature' leads to the curly, tubular branching characteristics consistent across the studio's body of work. In order to achieve structural #stability , each stripe assumes high degrees of curvature individually and high degrees of double curvature in accumulation -- amounting to extreme structural #rigidity throughout the project. #arch_shovel#archdaily