Registry / ai-ml / sherpa-onnx-core

sherpa-onnx-core

library1.13.3pypypi✓ verified 84d ago

Core shared libraries for sherpa-onnx, a cross-platform speech recognition and text-to-speech toolkit. Version 1.12.40 provides the underlying ONNX Runtime-based engines for ASR, VAD, and TTS, with package updates for various platforms. Release cadence is approximately semi-monthly.

ai-ml

pip install sherpa-onnx-core

github ↗package ↗

INSTALL

IMPORT

SIG · SHERPA-ONNX-CORE

sherpa-onnx-core

ai-mlpythonv1.13.3

Install

1.8s avg

Import

—

Disk

45MB

Pass rate

5/ 10

Env Coverage5 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.13.3 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

build_error

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 1.8s · import 0.000s · 47MB

45MB installed

● package 45MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

OfflineRecognizer

✓ import sherpa_onnx

✗ from sherpa_onnx import OfflineRecognizer

The recommended import is the module-level import; 'from sherpa_onnx import OfflineRecognizer' works but is less conventional.

OnlineRecognizer

✓ import sherpa_onnx

✗ from sherpa_onnx_core import OnlineRecognizer

sherpa-onnx-core does not expose a separate package; everything is under sherpa_onnx.

Basic offline ASR using pre-downloaded ONNX models.

import sherpa_onnx recognizer = sherpa_onnx.OfflineRecognizer.from_models( encoder="path/to/encoder.onnx", decoder="path/to/decoder.onnx", tokens="path/to/tokens.txt", ) wave = sherpa_onnx.read_wave("test.wav") result = recognizer.decode(wave) print(result.text)

Debug

Known issues

gotchaThe 'sherpa-onnx-core' package only contains shared libraries; the Python API is provided by 'sherpa-onnx'. Installing 'sherpa-onnx-core' alone will not give you importable Python modules.

fix

Install 'sherpa-onnx' instead: pip install sherpa-onnx

affects: all

breakingModel file formats may change between major releases. Models downloaded for version 1.9 may not work with 1.12.

fix

Always download the latest model files for your sherpa-onnx version.

affects: >=1.10

deprecatedThe 'sherpa_onnx.OfflineRecognizer' constructor signature changed in v1.10; 'from_models' is now the preferred factory method.

fix

Use 'OfflineRecognizer.from_models(...)' instead of 'OfflineRecognizer(...)'.

affects: >=1.10

Errors

Common errors & fixes

ImportError: cannot import name 'OfflineRecognizer' from 'sherpa_onnx'

The 'sherpa-onnx-core' package does not include the Python bindings; only the C libraries.

fix

Install 'sherpa-onnx' (pip install sherpa-onnx) which provides the Python API.

ModuleNotFoundError: No module named 'sherpa_onnx'

Neither 'sherpa-onnx' nor 'sherpa-onnx-core' is installed.

fix

Run 'pip install sherpa-onnx'.

RuntimeError: Model file not found: /path/to/encoder.onnx

The model path is incorrect or the model was not downloaded.

fix

Download the model files from the official model zoo and provide absolute paths.

Upgrade

Version history

1.13.3latest on PyPI · released Jun 15, 2026

Audit

Dependencies

No dependency data recorded yet.

Agent activity

16 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/k2-fsa/sherpa-onnx ↗

packagehttps://pypi.org/project/sherpa-onnx-core/ ↗