Qwen3-ASR-1.7B is an open-source automatic speech recognition (ASR) model designed for converting audio input into text. It supports local inference, making it suitable for privacy-sensitive or offline applications. Developers can integrate it into custom speech processing pipelines or products.
In the Voice, TTS & speech space, Qwen3 ASR 1.7B takes a focused approach. It focuses on transcribing spoken audio into text locally without relying on cloud services. It is built as an open-source project for speech technology developers. Qwen3 ASR 1.7B is open source under the BSD-3-Clause license. Qwen3 ASR 1.7B is available on the command line, and it can be self-hosted.
mig-ai builds and maintains Qwen3 ASR 1.7B, and the product first shipped in 2022. Development happens publicly on GitHub with 24.5k stars and 89 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Qwen3 ASR 1.7B occupies a relatively distinct niche. Key capabilities include speech recognition, audio transcription, and local inference.
Latest indexed changes and source events
mig-ai/Qwen3-ASR-1.7B discovered by the PulseGate indexer
Other apps tracked under the same category.
