Loading...
Market
How will Whisper Turbo rank in industry benchmarks by end of 2024?
2
Resolution / Starting Odds
Best performing model • 25%
Top 3 performing models • 25%
Top 5 performing models • 25%
Not in top 5 • 25%
Industry benchmark reports and publications
Story
OpenAI Unveils Whisper Turbo: 8x Faster, 2x Smaller, Transcribes 2 Minutes in 12 Seconds
Oct 1, 2024, 08:54 AM
On October 1, 2024, OpenAI released Whisper Turbo, a new version of its Whisper speech-to-text model. The optimized model offers 8 times faster transcription speed and uses 2 times fewer parameters than Whisper Large v3, with minimal degradation in accuracy. Whisper Turbo features a reduced model size of 809 million parameters and utilizes 4 decoder layers instead of 32. It is multilingual, supports both word and chunk-level timestamps, and is 40% more VRAM efficient. The model can transcribe two minutes of audio in approximately 12 seconds and can run locally in a browser using Transformers.js, making it accessible for applications with limited resources.
View original story
Similar markets
Less than 1 million users • 25%
1 to 5 million users • 25%
5 to 10 million users • 25%
More than 10 million users • 25%
Yes • 50%
No • 50%
English • 25%
Spanish • 25%
Mandarin • 25%
Other • 25%
Yes • 50%
No • 50%
Below 70% • 25%
70%-80% • 25%
80%-90% • 25%
Above 90% • 25%
Yes • 50%
No • 50%
Enterprise transcription services • 25%
Real-time translation services • 25%
Voice-controlled applications • 25%
Other • 25%
Coding • 25%
Hard Prompts • 25%
Math • 25%
Longer Queries • 25%
StepFun • 25%
OpenAI • 25%
o1-mini • 25%
Other • 25%