Downloads · 30 days
25
26% of all-time downloads
a1700878328/qwen3-asr-1.7b-onnx-int4
qwen3-asr-1.7b-onnx-int4 is a automatic speech recognition model from a1700878328. Use it when you need speech turned into text. It is set up for onnxruntime. The card lists the license as apache-2.0.
This directory contains a locally exported deployment build of Qwen/Qwen3-ASR-1.7B.
Downloads · 30 days
25
26% of all-time downloads
All-time downloads
95
Public
Repo size
3.5 GB
Likes
0
Public
Click a slice to open those files.
.data2 GB · 58%
From the Hugging Face model README
This directory contains a locally exported deployment build of
Qwen/Qwen3-ASR-1.7B.
This is a split native ONNX Runtime pipeline. It is not a sherpa-onnx model and cannot be dropped into a sherpa-onnx runner without an adapter.
Qwen/Qwen3-ASR-1.7B, Apache-2.0andrewleech/qwen3-asr-onnx4aee2ae0c355c7bc33bd5c09befec9e9eabd4b50The official model was downloaded and verified locally before export. The encoder, decoder-init, and decoder-step graphs all passed ONNX Runtime loading checks. CUDA validation rejects silent CPU fallback.
Run from the exporter repository:
$env:PYTHONUTF8 = "1"
uv sync
uv run python validate.py `
--model models/Qwen3-ASR-1.7B `
--onnx-dir release/qwen3-asr-1.7b-onnx-int4 `
--audio C:\path\to\test.wav `
--provider cuda `
--max-tokens 1024
The validation command also loads the original PyTorch model for comparison, so it is slower and requires the original weights. Production inference needs only the ONNX model files, tokenizer, audio preprocessing, and ONNX Runtime.
Measured on an RTX 5070 Ti 16 GB:
| Audio | Duration | ONNX encoder | ONNX decoder | Total | RTF |
|---|---|---|---|---|---|
| Japanese news/narration | 108.9 s | 0.54 s | 51.29 s | 51.83 s | 0.48 |
| Japanese dialogue | 104.7 s | 0.53 s | 47.42 s | 47.95 s | 0.46 |
Normalized character error rate against the two supplied transcripts was 3.21% and 5.14%, or 4.20% aggregate. Punctuation, spaces, and symbol differences were excluded. A company RTX 4090 should be faster, but it must be benchmarked on that machine before setting concurrency limits.
uv run python export.py `
--model models/Qwen3-ASR-1.7B `
--output output/qwen3-asr-1.7b-fp32 `
--device cpu `
--dtype fp32 `
--opset 18 `
--no-share-weights
uv run python share_weights.py output/qwen3-asr-1.7b-fp32 --verify
uv run python quantize_nbits.py `
--input output/qwen3-asr-1.7b-fp32 `
--output output/qwen3-asr-1.7b-fp32 `
--bits 4 `
--block-size 64 `
--accuracy-level 4 `
--algo rtn
uv run python share_weights.py `
output/qwen3-asr-1.7b-fp32 `
--suffix int4 `
--verify
uv run python export_encoder_native_fp16.py `
--model models/Qwen3-ASR-1.7B `
--output output/qwen3-asr-1.7b-fp32/encoder.int4.onnx `
--opset 18 `
--verify
uv run python convert_embed_fp16.py `
--model-dir output/qwen3-asr-1.7b-fp32
The release directory was assembled from the native FP16 encoder, shared INT4 decoder pair, shared INT4 external weights, FP16 embeddings, tokenizer, and configuration files.