Qwen ASR
No written verdict yet. Here is what commenters said.
6recommend
0warn against
Feb 27, 2026first mention
Oct 20, 2026latest mention
Why people recommend it
“qwen recognized correctly 168”
has a heavy accenton “Whistle: Speech to Text in 16.9 MB”
Show 3 more
“give it to qwen asr for raw transcription”
“I would try Qwen-ASR: https://qwen.ai/blog?id=qwen3asr”
“Qwen ASR and TTS are really good.”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Who recommends it in their own words
Threads where it came up
- Voxtral 3 1 mention
- Whistle: Speech to Text in 16.9 MB 1 mention
- Ask HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT? 1 mention
- Cohere Transcribe: Speech Recognition 1 mention
- My Journey to a reliable and enjoyable locally hosted voice assistant 1 mention
- Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU acceleration 1 mention
Also written as qwen-asr, Qwen-ASR. Data: qwen-asr.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 6
“I found Qwen ASR and QwenTTS to be quite good”
“qwen recognized correctly 168”
“give it to qwen asr for raw transcription”
“I would try Qwen-ASR: https://qwen.ai/blog?id=qwen3asr”
“Qwen ASR and TTS are really good.”
“Qwen-asr can easily transcribe live radio (see README) in any random laptop.”