Skip to content
Live
Trending storyPast story

Baseten optimized Qwen3-ASR to achieve low-cost batch speech transcription

1 reports1 outlets21 days agoUpdate

The story so far

AI overview

Baseten has achieved low-cost, high-throughput batch speech transcription by optimizing Qwen3-ASR 1.7B on the Baseten platform. Its vLLM stack supports 7 times the throughput of standard vLLM on an RTX PRO 6000, with a maximum of 3,128 times the real-time factor, enhancing performance through native audio decoding, FP8 KV cache quantization, and reducing host-device synchronization.

AI-written from the reports · Updated 21 days ago

Coverage timeline

Follow the coverage to see every side of the story.

29 Oct
  1. Baseten Blog
    The fastest, lowest-cost batch transcription with Qwen3-ASR

    Baseten achieved the lowest cost per minute for batch speech transcription by optimizing Qwen3-ASR 1.7B (175B parameters, 5.4% WER) on Baseten. Its vLLM stack supports 7 times the throughput of standard vLLM on RTX PRO 6000, with a maximum real-time factor of 3,128, enhanced by native audio decoding, FP8 KV cache quantization, and reduced host-device synchronization.