#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
🕵️#MEGA Bubblemaps: MEGA tokens were distributed among 8,360 addresses, with approximately 50% of addresses still holding all the tokens. About 40% of addresses have sold them completely, and around 10% of addresses have sold only a portion of the coins. link
Guillaume Faye left us on March 6, 2019, at the age of 69. He was a unique figure who leaves behind an extensive body of work. Like the ancient Greek heroes of old, he will achieve immortality if we continue to share his ideas. Guillaume laid the foundations—now it is up to us, dear comrades, to build the sanctuary of European civilization!
#MEGA
¿Que puede hacer este bot?
@MegaUploadXbot
Este bot cargará archivos y vinculará directamente a su cuenta de Mega entre otras características.
Idioma: inglés
(Visto en @botsgram_cu)
#mega