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

Hashtags

#python #deep_learning #inference #openai #quantization #speech_recognition #speech_to_text #transformer #whisper

Results

1 similar post found

Search: #documentleak

当前筛选 #documentleak清除筛选

Venture Village Wall 🦄

@venturevillagewall · Post #3590 · 12/20/2024, 12:23 PM

Find similar View

Google's Growth Dilemma Revealed Google faces a challenge with 5.5 billion users searching three times daily, leading to a near 98% penetration of its services. The company's pressure to show growth for investors may have led to risky strategies, including diversifying user journeys to boost commercial queries. A leaked document outlines these changes aimed at enhancing growth beyond organic metrics. Find out more in our podcast: Кухня. 📈 Listen here: Кухня Podcast For the full leaked document: Leaked Document #Google#Search#Users#Growth#Investment#Penetration#CommercialQueries#Tech#Strategy#Marketing#DocumentLeak#Podcast#DigitalMarketing#UserJourney#Innovation#Business#Alphabet#TechCulture#Earnings#MarketTrends