Downloads · 30 days
0
thieunv-asilla/sherpa-onnx-qwen3-asr-1.7B-int8
sherpa-onnx-qwen3-asr-1.7B-int8 is a automatic speech recognition model from thieunv-asilla. Use it when you need speech turned into text. It is set up for sherpa-onnx. The card lists the license as apache-2.0.
INT8 ONNX build of Qwen3-ASR-1.7B in the sherpa-onnx fromqwen3asr layout, for on-device multilingual speech recognition (no Python at runtime).
Downloads · 30 days
0
Access
Public
Updated Jul 23, 2026
Repo size
2.4 GB
Likes
1
Public
Click a slice to open those files.
.onnx2.4 GB · 100%
From the Hugging Face model README
INT8 ONNX build of Qwen3-ASR-1.7B in the sherpa-onnx
from_qwen3_asr layout, for on-device multilingual speech recognition (no Python at runtime).
Qwen/Qwen3-ASR-1.7B (Apache-2.0)export_qwen3_asr_onnx.py --device cpu --max-total-len 512, INT8 dynamic quantization).conv_frontend.onnx # log-mel / conv frontend
encoder.int8.onnx # audio encoder (int8)
decoder.int8.onnx # text decoder w/ KV cache (int8, ~2 GB)
tokenizer/vocab.json
tokenizer/merges.txt
tokenizer/tokenizer_config.json
import sherpa_onnx
rec = sherpa_onnx.OfflineRecognizer.from_qwen3_asr(
conv_frontend="conv_frontend.onnx",
encoder="encoder.int8.onnx",
decoder="decoder.int8.onnx",
tokenizer="tokenizer",
num_threads=4,
)
s = rec.create_stream()
s.accept_waveform(16000, samples_f32_mono) # 16 kHz mono float32
rec.decode_stream(s)
print(s.result.text)
Requires sherpa-onnx >= 1.13.4 (adds from_qwen3_asr).
Apache-2.0, inherited from Qwen/Qwen3-ASR-1.7B. Attribution to the Qwen team (Alibaba Cloud) and the sherpa-onnx / export-script authors.