Qwen3-ASR-1.7B is an automatic speech recognition model from the Qwen3 family. It processes audio inputs and generates text transcriptions with support for multiple languages. The model uses a specialized tokenizer for audio tokens and is designed to be efficient while delivering high accuracy for real-world speech recognition tasks.
In the Speech to text space, Qwen3 ASR 1.7B takes a focused approach. It focuses on converting spoken audio into accurate text transcripts using a compact, high-performance model. It is built as an open-source project for developers building speech-to-text applications. The project is open source (BSD-3-Clause). It runs on the web, the command line, and API.
Behind Qwen3 ASR 1.7B is Qwen, based in China, and it first shipped in 2022. Development happens publicly on GitHub with 24.5k stars and 83 commits in the last 90 days. PulseGate's similarity index places it among 11 comparable projects. Key capabilities include Automatic Speech Recognition, Audio Processing, and Multilingual Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do