kaldifst
Decision gist · record as of 2026-08-14
Yes, if you need OpenFst or Kaldi FST operations in Python and are on a supported platform (Python 3.10–3.12, macOS/Linux/Windows). The permissive license, active maintenance, zero known vulnerabilities, and prebuilt wheels make it straightforward to adopt. If you require Python 3.8 support, verify source-build feasibility first.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.8; prebuilt wheels available for Python 3.10, 3.11, 3.12 on select platforms.
- Medium install friction due to compiled wheels; prebuilt binaries available for Python 3.10, 3.11, and 3.12 on macOS (Intel and ARM), Linux (x86_64 and aarch64), and Windows.
- Last release 127 days ago; repository is active with 56 stars.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.
last release 2026-04-09 (127 days) · last repo commit 2026-04-09 · 56 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 295,858 downloads/mo, #7,912 on PyPI
Alternatives
Verify before relying
pip install kaldifst
import kaldifst
# Use OpenFst operations (e.g., fstdeterminizestar) via the wrapper- Specific API surface and which Kaldi FST extensions are exposed beyond fstdeterminizestar.
- Whether the package supports Python 3.8 via source build or only via prebuilt wheels for 3.10–3.12.
- Performance characteristics and typical use patterns in speech recognition or NLP pipelines.
What it is and what it does
Kaldifst is a Python wrapper around OpenFst and selected extensions from the Kaldi speech recognition toolkit. It lets you use finite-state transducer operations—such as fstdeterminizestar—directly from Python without needing to install Kaldi itself. The package is compiled to native code and distributed as prebuilt wheels for common platforms and Python versions.
It is primarily used in speech recognition, language modeling, and other NLP tasks where finite-state machines are part of the pipeline. The wrapper bridges the gap between high-level Python code and the lower-level FST algorithms, making it easier to integrate Kaldi-style FST operations into Python applications.
Use it for
- Build speech recognition pipelines that need FST determinization and composition operations.
- Integrate finite-state transducers into Python-based NLP workflows without a full Kaldi installation.
- Perform language model composition and optimization using OpenFst algorithms from Python.
- Prototype and experiment with FST-based algorithms in interactive environments.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need OpenFst or Kaldi FST operations in Python and are on a supported platform (Python 3.10–3.12, macOS/Linux/Windows).
The permissive license, active maintenance, zero known vulnerabilities, and prebuilt wheels make it straightforward to adopt. If you require Python 3.8 support, verify source-build feasibility first.
Install
kaldifst on PyPI
Before you install
Medium install friction due to compiled wheels; prebuilt binaries available for Python 3.10, 3.11, and 3.12 on macOS (Intel and ARM), Linux (x86_64 and aarch64), and Windows. Last release 127 days ago; repository is active with 56 stars.
Requires Python >=3.8; prebuilt wheels available for Python 3.10, 3.11, 3.12 on select platforms.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.
Quickstart
pip install kaldifst
import kaldifst
# Use OpenFst operations (e.g., fstdeterminizestar) via the wrapperVerify before relying
- Specific API surface and which Kaldi FST extensions are exposed beyond fstdeterminizestar.
- Whether the package supports Python 3.8 via source build or only via prebuilt wheels for 3.10–3.12.
- Performance characteristics and typical use patterns in speech recognition or NLP pipelines.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 127 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 295,858 / month, #7,912 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: C++Programming Language :: PythonTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: kaldifst-1.8.0-cp310-cp310-macosx_10_15_universal2.whl; kaldifst-1.8.0-cp310-cp310-macosx_10_15_x86_64.whl; kaldifst-1.8.0-cp310-cp310-macosx_11_0_arm64.whl; kaldifst-1.8.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl; kaldifst-1.8.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; kaldifst-1.8.0-cp310-cp310-win32.whl; kaldifst-1.8.0-cp310-cp310-win_amd64.whl; kaldifst-1.8.0-cp311-cp311-macosx_10_15_universal2.whl; kaldifst-1.8.0-cp311-cp311-macosx_10_15_x86_64.whl; kaldifst-1.8.0-cp311-cp311-macosx_11_0_arm64.whl; kaldifst-1.8.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl; kaldifst-1.8.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; kaldifst-1.8.0-cp311-cp311-win32.whl; kaldifst-1.8.0-cp311-cp311-win_amd64.whl; kaldifst-1.8.0-cp312-cp312-macosx_10_15_universal2.whl; kaldifst-1.8.0-cp312-cp312-macosx_10_15_x86_64.whl; kaldifst-1.8.0-cp312-cp312-macosx_11_0_arm64.whl; kaldifst-1.8.0-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl; kaldifst-1.8.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; kaldifst-1.8.0-cp312-cp312-win32.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 › “finite state transducer python”
- kaldifstPython wrapper for OpenFst and Kaldi extensions, providing…
- wetextNormalizes and denormalizes text in Chinese, English, and Japanese…
- fysomFysom is a finite state machine library that lets you define states,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also kaldi-native-fbank · kaldialign · pynini · kaldiio · kaldi-python-io · funasr · vosk · nemo-text-processing · django-fsm-2 · onnx-asr