onnx-asr
A lightweight Python package for Automatic Speech Recognition using ONNX models
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has low install friction, carries a permissive MIT license, and solves a real problem—lightweight offline speech recognition without PyTorch or heavy dependencies. It supports modern models and diverse hardware. No known vulnerabilities. Install it if you need ASR inference in Python without framework overhead.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Most models have a maximum audio length of 20–30 seconds; longer audio requires Voice Activity Detection (VAD).
- Low friction: pure Python wheel with only numpy and typing-extensions as runtime dependencies.
- Active maintenance with a release 30 days ago and 361 repository stars.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions.
last release 2026-07-15 (30 days) · last repo commit 2026-08-04 · 361 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 230,295 downloads/mo, #9,113 on PyPI
Alternatives
Verify before relying
pip install onnx-asr[cpu,hub]
import onnx_asr
model = onnx_asr.load_model("nemo-parakeet-tdt-0.6b-v3")
result = model.recognize("test.wav")
print(result)- Whether the package's claimed support for CUDA, TensorRT, CoreML, DirectML, ROCm, and WebGPU requires additional system libraries or environment setup beyond pip install.
- Performance characteristics on specific hardware (e.g., actual RTFx values on your target device) beyond the published benchmarks.
- Whether quantized model variants are automatically downloaded or require manual setup.
What it is and what it does
onnx-asr is a Python library for speech-to-text inference using ONNX-format models. It wraps modern ASR architectures (NeMo Conformer/Parakeet/Canary, GigaAM, Kaldi Icefall Zipformer, T-Tech T-one, and OpenAI Whisper) with preprocessing and decoding logic, letting you load a model and transcribe audio in a few lines of code. The package is designed to be lightweight—it requires only numpy and typing-extensions, avoiding heavy dependencies like PyTorch or Transformers—and runs on diverse hardware from IoT devices to GPU servers.
You provide either a WAV file or NumPy array, and the package handles resampling, log-mel spectrogram computation, and greedy-search decoding. It supports batch processing, Voice Activity Detection for long-form audio, token-level timestamps, and log probabilities. Models load from Hugging Face or local directories, including quantized versions. The library is actively maintained, fully typed, and includes both a Python API and a command-line interface.
Use it for
- Transcribe audio files offline without cloud dependencies or heavy ML frameworks in production services.
- Build speech-to-text features on edge devices or IoT hardware with constrained resources.
- Process long-form audio recordings using Voice Activity Detection to split and recognize speech segments.
- Integrate multilingual ASR (Parakeet v3, Canary, GigaAM Multilingual) into applications requiring non-English transcription.
- Benchmark or compare ONNX-based ASR models across different hardware (CPU, CUDA, TensorRT, CoreML).
- Develop custom ASR pipelines by loading quantized or fine-tuned ONNX models from Hugging Face.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has low install friction, carries a permissive MIT license, and solves a real problem—lightweight offline speech recognition without PyTorch or heavy dependencies. It supports modern models and diverse hardware. No known vulnerabilities. Install it if you need ASR inference in Python without framework overhead.
Install
onnx-asr on PyPI
Before you install
Low friction: pure Python wheel with only numpy and typing-extensions as runtime dependencies. Active maintenance with a release 30 days ago and 361 repository stars. Supports Python 3.10 through 3.14.
Most models have a maximum audio length of 20–30 seconds; longer audio requires Voice Activity Detection (VAD).
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions.
Quickstart
pip install onnx-asr[cpu,hub]
import onnx_asr
model = onnx_asr.load_model("nemo-parakeet-tdt-0.6b-v3")
result = model.recognize("test.wav")
print(result)Verify before relying
- Whether the package's claimed support for CUDA, TensorRT, CoreML, DirectML, ROCm, and WebGPU requires additional system libraries or environment setup beyond pip install.
- Performance characteristics on specific hardware (e.g., actual RTFx values on your target device) beyond the published benchmarks.
- Whether quantized model variants are automatically downloaded or require manual setup.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesnumpytyping-extensions |
| Maintenance | Actively maintained 30 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 230,295 / month, #9,113 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: Free Threading :: 2 - BetaTopic :: Multimedia :: Sound/Audio :: SpeechTopic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python ModulesTyping :: Typed |
Evidence: onnx_asr-0.12.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “onnx asr models”
- onnx-asrAutomatic Speech Recognition using ONNX models with minimal…
- sherpa-onnxSherpa-onnx runs speech recognition, text-to-speech, speaker…
- nemo-toolkitnemo-toolkit provides a PyTorch framework for building, training, and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Libraries packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
Provides parsing, arithmetic, and recurrence rule computation for dates and times, with timezone support and iCalendar RFC compliance.
Install it if you need to parse flexible date strings, compute relative dates, handle timezones, or work with recurrence rules—it's the de facto choice for these tasks.
Six provides utility functions to write Python code that runs on both Python 2.7 and Python 3.3+, smoothing over language differences between the two versions.
pytest is a testing framework that lets you write test functions using plain assert statements and automatically discovers and runs them, with detailed failure reporting.
See also sherpa-onnx · sherpa-onnx-core · funasr · nemo-toolkit · pocketsphinx · SpeechRecognition · silero-vad · whisperx · qwen-asr · speechbrain