qwen
Qwen: Qwen3 ASR 1.7B
qwen/qwen3-asr-1.7b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen that takes audio input and returns transcriptions. Its documentation says it performs language identification and transcription across 30 languages and 22 Chinese dialects, including English accents from multiple regions, and that a single model handles both streaming and offline inference, including long audio. The vendor reports state-of-the-art results among open-source ASR models and competitiveness with strong commercial APIs, but no independent benchmark data was provided in this pack. Word-level timestamps require pairing it with the separate Qwen3-ForcedAligner-0.6B.[1][2]
Strengths
- Broad reported language coverage: 30 languages plus 22 Chinese dialects and multiple English accents, across speech, singing voice, and songs with background music.[2]
- Single model supports streaming and offline inference for long audio, with an open inference toolkit offering vLLM-based batch and asynchronous serving.[1][2]
- Openly released under Apache-2.0 with a dedicated qwen-asr Python package supporting transformers and vLLM backends.[2]
Limitations
- Streaming inference is only available through the vLLM backend and does not support batch inference or returning timestamps.[2]
- Timestamp output depends on the separate Qwen3-ForcedAligner-0.6B model, which covers only 11 languages and up to five minutes of speech.[2]
- Accuracy and competitiveness claims are vendor-reported; this pack contains no independent evaluation, so validate quality and latency on your own audio workloads.[1][2]
Where to use it
- Multilingual transcription pipelines that need automatic language identification across the documented languages and dialects.[2]
- Real-time captioning or live transcription via the vLLM streaming backend, where batching and timestamps are not required.[1][2]
- Transcribing sung vocals or songs with background music, an audio type the documentation explicitly lists as supported.[2]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3 ASR 1.7BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3 ASR 1.7BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference...
Specifications
- Model ID
- qwen/qwen3-asr-1.7b
- Canonical ID
- qwen/qwen3-asr-1.7b-20260813
- Creator
- qwen
- Added to OpenRouter
- 13.08.2026
- Context length
- 0
- Modality
- audio->transcription
- Input modalities
- audio
- Output modalities
- transcription
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| PrimeIntellectbf16 | 0 | — | — | — | — | 100% |
| DeepInfra | 0 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.