Tag: Insanely Fast Whisper

Cohere Transcribe: The Open-Weight ASR Model That Outperforms Whisper with 5.42% Word Error Rate

Cohere's new open-weight ASR model Transcribe achieves 5.42% WER, outperforming Whisper and ElevenLabs, with full commercial deployment flexibility under Apache-2.0 license.

openx_editor April 3, 2026 2 mins read

AI Tools, Open Source

Insanely Fast Whisper: Transcribe 2.5 Hours of Audio in Under 98 Seconds with OpenAI’s Latest Model

Insanely Fast Whisper is a community-built CLI tool that leverages Flash Attention 2, batch processing, and Hugging Face Transformers to transcribe 150 minutes of audio using Whisper Large v3 in just 98…

openx_editor March 27, 2026 3 mins read