qwen3-asr-mnn
Qwen3-ASR (0.6B / 1.7B) speech recognition on pure CPU via MNN — no PyTorch, no transformers, no GPU required at runtime.
- Fast: avg RTF ≈ 0.06 (0.6B) / 0.15 (1.7B) on Apple Silicon — 2.3×–2.6× faster than the HF PyTorch fp32 baseline
- Accurate: token-identical to the HF fp32 reference on standard samples (CER 0.0000 for 0.6B); remaining 1.7B differences match the official HF bf16 inference
- Zero-config CLI: models are downloaded automatically from HuggingFace on first use
- Lightweight: runtime deps are only
numpy,soundfile,soxr,huggingface_hub
Models: https://huggingface.co/yunfengwang/Qwen3-ASR-MNN (fp16 weights, exported with MNN llmexport)
Install
pip install qwen3-asr-mnn
# or run directly without installing:
uvx qwen3-asr-mnn audio.wav
Prebuilt native extension: macOS arm64, CPython 3.10–3.13. Other platforms can build from source with native/build_native.sh (requires a local MNN tree).
CLI
qwen3-asr-mnn speech.wav # 0.6B (default), auto-download model
qwen3-asr-mnn speech.wav --model 1.7b # higher accuracy
qwen3-asr-mnn speech.wav --json # full result (ids, rtf, timing)
qwen3-asr-mnn https://example.com/a.wav # URL input
Any common sample rate / channel layout is accepted (auto-resampled to 16 kHz mono).
Python API
The engine is loaded once and reused — no repeated initialization cost:
from qwen3_asr_mnn import Qwen3ASR
asr = Qwen3ASR(model="0.6b") # downloads MNN model on first construction
text = asr.transcribe("a.wav") # fast, engine already warm
text = asr.transcribe("b.wav")
# details: language, token ids, RTF, encoder/prefill/decode timings
r = asr.transcribe_result("a.wav")
print(r["text"], r["language"], f"RTF={r['rtf']:.3f}")
# numpy waveform input (e.g. streaming)
import numpy as np
wav = np.zeros(16000, dtype=np.float32)
print(asr.transcribe(wav, sample_rate=16000))
# precomputed log-mel [128, T] input
from qwen3_asr_mnn import extract_mel_from
mel, valid = extract_mel_from("a.wav")
print(asr.transcribe_mel(mel, valid)["text"])
Qwen3ASR parameters: model ('0.6b'/'1.7b'), model_dir (local dir or HF repo id; defaults to auto-download), threads (default 8), precision ('low' fp16 math — default, token-identical to 'normal' fp32 math but ~2× faster), max_new_tokens.
How it works
audio ──▶ log-mel (numpy STFT, HF-aligned) ──▶ audio_encoder.mnn (windowed, 104-frame static graph)
──▶ prompt splice (text embeddings + audio embeddings) ──▶ llm.mnn (KV-cache, fp16, greedy)
──▶ text
The audio encoder uses 8×13=104-frame attention windows with frame-level key masking, mathematically equivalent to HF's packed cu_seqlens attention (max error 0 vs HF in fp32). The LLM decoder is exported with MNN llmexport --quant_bit 16 and driven by the MNN Transformer::Llm C++ engine.
License
Apache-2.0
Metadata
Release files for qwen3-asr-mnn 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| qwen3_asr_mnn-0.1.0.tar.gz | 7.3 MB | Without provenance | Details for qwen3_asr_mnn-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| qwen3_asr_mnn-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for qwen3_asr_mnn-0.1.0-py3-none-any.whl |
Total release size: 14.6 MB
Release files / qwen3_asr_mnn-0.1.0.tar.gz
| Download URL | qwen3_asr_mnn-0.1.0.tar.gz |
|---|---|
| Size | 7.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7e52e42af30ce81f801c78074e1b315d1f20adaf5e631c4e8ac0eac8857f0176
|
|
BLAKE2b-256 checksum How to use checksums |
e8d442f6b9601596ee82174ce4487dd6af8787978b5a54f5ced074c1b3f61834
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.29 {"installer":{"name":"uv","version":"0.11.29","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / qwen3_asr_mnn-0.1.0-py3-none-any.whl
| Download URL | qwen3_asr_mnn-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.3 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fe1adc977e8d2e0a73f214a7d6b09eb79292806191a169cad7d69b7c6949bded
|
|
BLAKE2b-256 checksum How to use checksums |
1ce79e4069310ef4cef86be7904d6d53603a9567b22ad834d18f4a45ac6707d7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.29 {"installer":{"name":"uv","version":"0.11.29","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for qwen3-asr-mnn 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.