Speech-to-text
Qwen3-ASR 1.7B requirements, license & speed
By Alibaba Qwen · released 2026-01-28 · 2.35B parameters
Commercial useYes
Min memoryNot stated
Runs on CPUUnknown
StreamingYes
Key facts
- License
- apache-2.0 source
- Commercial use
- Yes sourceApache-2.0
- Parameters
- 2.35B sourcesafetensors parameter count
- Minimum memory
- Not stated by source
- Runs on CPU
- Unknown
- Streaming
- Yes sourceStreaming only with the vLLM backend
- Voice cloning
- n/a (speech-to-text)
- Languages
- 30 languages + 22 Chinese dialects (52 total) source
- Released
- 2026-01-28 sourceHugging Face repo creation date (proxy for release date)
- Gated on HF
- No
Measured speed & memory
Benchmark pending. We haven't measured Qwen3-ASR 1.7B yet. Planned targets: Raspberry Pi 5, CPU-only x86, Apple Silicon Mac and consumer GPUs. Get notified.
Accuracy
We don't run accuracy evals. For word error rate, check the Hugging Face Open ASR Leaderboard.
Similar STT models
Spotted an error? Report it. Every fact links to the model card or repo it came from.