GitHub - openai/whisper
github.com
external-link
Contribute to openai/whisper development by creating an account on GitHub.

On Wednesday, OpenAI released a new open source AI model called Whisper that recognizes and translates audio at a level that approaches human recognition ability. It can transcribe interviews, podcasts, conversations, and more.

OpenAI trained Whisper on 680,000 hours of audio data and matching transcripts in 98 languages collected from the web. According to OpenAI, this open-collection approach has led to “improved robustness to accents, background noise, and technical language.” It can also detect the spoken language and translate it to English.

Masterofballs
mod
link
fedilink
113d

This would be really useful for generating movie subtitles.

Any tech realated news. Computers, games, programming all welcome

  • 0 users online
  • 1 user / day
  • 1 user / week
  • 7 users / month
  • 11 users / 6 months
  • 4 subscribers
  • 48 Posts
  • 33 Comments
  • Modlog