Qwen3-ASR 1.7B
Hacker ApprovedRanked 9 of 25 speech recognition models by recommenders
People recommend this open speech-to-text model for accurate transcription that runs fast on local hardware, including laptops and Apple Silicon. Critics say it is only good for English.
People recommend this open speech-to-text model for accurate transcription that runs fast on local hardware, including laptops and Apple Silicon. Critics say it is only good for English.
18 people gave an opinion
- recommend it
- 15
- criticize it
- 3
- approval share
- 83%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 15 people recommend itNeeds 10 or more, met.
- 5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Accurate transcription, close to Whisper Large
“I'm quite happy with how it performs (both transcription quality and speed on rtx5080).”
Comment from 8 Oct 2026 in “Whistle: Speech to Text in 16.9 MB” “it's the second most accurate open model after the one in this post”
Comment from 28 Oct 2026 in “Nvidia Nemotron 3.5 Transcribe: open ASR for 40 languages” “I found Qwen ASR and QwenTTS to be quite good, and not too large.”
Comment from 20 Oct 2026 in “Voxtral 3” - Comment from 9 Oct 2026 in “Whistle: Speech to Text in 16.9 MB”
- Comment from 11 Sep 2026 in “Expanding the Pareto Frontier for Realtime Transcription”
Fast and runs on ordinary laptops
“I'm quite happy with how it performs (both transcription quality and speed on rtx5080).”
Comment from 8 Oct 2026 in “Whistle: Speech to Text in 16.9 MB” “Qwen-asr can easily transcribe live radio (see README) in any random laptop.”
Comment from 27 Feb 2026 in “Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU acceleration” “Qwen ASR is faster than OpenAI Whisper on Apple Silicon from my tests”
Comment from 16 Mar 2026 in “My Journey to a reliable and enjoyable locally hosted voice assistant” Beats Whisper and Parakeet for some users
“Qwen ASR is faster than OpenAI Whisper on Apple Silicon from my tests”
Comment from 16 Mar 2026 in “My Journey to a reliable and enjoyable locally hosted voice assistant” “it seems to work very well, at least as well as Whisper Large”
Comment from 9 Oct 2026 in “Whistle: Speech to Text in 16.9 MB” “I find Parakeet or Qwen ASR better.”
Comment from 28 Oct 2026 in “Nvidia Nemotron 3.5 Transcribe: open ASR for 40 languages” Pure Swift on MLX, no Python
“No Python, no server, no CoreML — pure Swift through MLX.”
Comment from 3 Mar 2026 in “Full speech pipeline in native Swift/MLX – ASR, TTS, speech-to-speech, on-device” “bundles ASR, TTS, and PersonaPlex in one Swift package”
Comment from 5 Mar 2026 in “Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift”
What people warn about
Each mark is one comment
Weaker outside English
“Qwen ASR (very good, but only for English)”
Comment from 28 Jul 2026 in “Show HN: Yap – OSS on-device voice dictation for macOS with no model to download” “not as good for others (like qwen ASR)”
Comment from 17 Mar 2026 in “Mistral Releases Leanstral”
Other speech recognition models people recommend
The four most recommended other speech recognition models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| OpenAI Whisper | 164 | 53 | 76% | 12 | — | Approved |
| NVIDIA Parakeet | 144 | 27 | 84% | 12 | — | Approved |
| Mistral Voxtral | 69 | 27 | 72% | 8 | — | Approved |
| Moonshine open-weights STT models | 37 | 13 | 74% | 7 | — | Approved |
| Qwen3-ASR 1.7BThis page | 15 | 3 | 83% | 6 | — | Approved |
What people said
19 of the 21 comments that mention it, newest first. Each links to the original comment.
“I find Parakeet or Qwen ASR better.”
“it's the second most accurate open model after the one in this post”
“I found Qwen ASR and QwenTTS to be quite good, and not too large.”
“it still makes a lot of weird mistakes”
“it seems to work very well, at least as well as Whisper Large”
“was slow as all hell to respond”
“I'm quite happy with how it performs (both transcription quality and speed on rtx5080).”
“qwen recognized correctly 168”
“Leading position on private leaderboard on HF”
“Qwen3-ASR 1.7B is an excellent OSS Speech-to-Text model.”
“it holds up way better with background noise”
“Qwen ASR (very good, but only for English)”
“I'd also look at the Qwen ASR models, also Chinese made, by Alibaba”
“See the very bottom of the page for a transcription with timestamps.”
“not as good for others (like qwen ASR)”
“Qwen ASR is faster than OpenAI Whisper on Apple Silicon from my tests”
“bundles ASR, TTS, and PersonaPlex in one Swift package”
“No Python, no server, no CoreML — pure Swift through MLX.”
“Qwen-asr can easily transcribe live radio (see README) in any random laptop.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.