---
format: "aidr-story-markdown/v1"
id: "53a2abbe2c6255bc23009f8b683cd6118d3876babf40359d7dc70660790979c9"
canonical_url: "https://aidr.today/53a2abbe?lang=en"
title: "Baseten Cuts Qwen3-ASR Batch Transcription Time to Under 5 Seconds Per Hour"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-28T22:15:38.000Z"
category: "Infra"
topics: ["inference"]
source_urls: ["https://huggingnews.com/ai/baseten-cuts-qwen3-asr-batch-transcription-time-to-under-5-seconds-per-h-2051ca47","https://marketbrief.now/ai/baseten-cuts-qwen3-asr-batch-transcription-time-to-under-5-seconds-per-h-2051ca47"]
summary: "Baseten has improved the processing speed of the Qwen3-ASR 1.7B open-weight model, enabling transcription of an hour of audio in less than five seconds at a cost of $0.0013 per hour, achieving 7x the throughput of stock vLLM on a single GPU."
---

# Baseten Cuts Qwen3\-ASR Batch Transcription Time to Under 5 Seconds Per Hour

> [Open the canonical story](<https://aidr.today/53a2abbe?lang=en>)

**Published:** 2026-10-28T22:15:38.000Z
**Category:** Infra
**Topics:** inference

## Summary

Baseten has improved the processing speed of the Qwen3\-ASR 1\.7B open\-weight model, enabling transcription of an hour of audio in less than five seconds at a cost of $0\.0013 per hour, achieving 7x the throughput of stock vLLM on a single GPU\.

## Sources

- [Story source](<https://huggingnews.com/ai/baseten-cuts-qwen3-asr-batch-transcription-time-to-under-5-seconds-per-h-2051ca47>)
- [Story source](<https://marketbrief.now/ai/baseten-cuts-qwen3-asr-batch-transcription-time-to-under-5-seconds-per-h-2051ca47>)