One interface to run and compare any speech-to-text model — local & cloud.
Project description
ASRKit
One interface to run and compare any speech-to-text model — local & cloud.
一套接口，跑遍端云所有语音识别。
⚠️ Placeholder release. This
0.0.1reserves the name while ASRKit is under active development. It does not yet provide functionality. Watch github.com/asrkit/asrkit for the first working release.
What ASRKit will be
ASRKit is the Ollama + LiteLLM for speech recognition:
- Local models,
pulland go — run open-source ASR models (SenseVoice, Paraformer, Zipformer, Whisper, Moonshine, Parakeet …) with one command, models downloaded on demand. - Cloud APIs, one string away — call hosted ASR (Volcengine, DashScope, OpenAI, Deepgram …) through the exact same interface, bring your own key.
- One protocol across edge and cloud — a single contract, an OpenAI-compatible endpoint, and a built-in
benchto compare them all on the same ruler.
Apache-2.0. Your audio and keys never pass through us — ASRKit runs on your machine.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file asrkit-0.0.1.tar.gz.
File metadata
- Download URL: asrkit-0.0.1.tar.gz
- Upload date:
- Size: 1.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d27eb65ce56f8dfd403ffc8f2d9102ec6f45934d7b01cac59522e1cba0527bb0
|
|
| MD5 |
1be895272df2d6e0b22a1e173a16ac52
|
|
| BLAKE2b-256 |
10fac46e9160ce7ff8ab1066e5d2cd04c1b318076909f506baad5ba95a585653
|
File details
Details for the file asrkit-0.0.1-py3-none-any.whl.
File metadata
- Download URL: asrkit-0.0.1-py3-none-any.whl
- Upload date:
- Size: 2.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
902a2fdda0abbd3d31f8a32e5f192b26b65226be056c99d415e6b9ee190775be
|
|
| MD5 |
595e81e6a64228a27fe8b80f27489998
|
|
| BLAKE2b-256 |
ce99fbf263b90dc0a5c7c5f9044d948e98a1505211b2a0375617e423960da940
|
