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

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.