asrkit 0.0.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- asrkit/__init__.py +7 -0
- asrkit-0.0.1.dist-info/METADATA +37 -0
- asrkit-0.0.1.dist-info/RECORD +4 -0
- asrkit-0.0.1.dist-info/WHEEL +4 -0
asrkit/__init__.py
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: asrkit
|
|
3
|
+
Version: 0.0.1
|
|
4
|
+
Summary: One interface to run and compare any speech-to-text model — local & cloud.
|
|
5
|
+
Project-URL: Homepage, https://github.com/asrkit/asrkit
|
|
6
|
+
Project-URL: Repository, https://github.com/asrkit/asrkit
|
|
7
|
+
Author: ASRKit
|
|
8
|
+
License: Apache-2.0
|
|
9
|
+
Keywords: asr,speech-recognition,speech-to-text,stt,transcription,whisper
|
|
10
|
+
Classifier: Development Status :: 1 - Planning
|
|
11
|
+
Classifier: Intended Audience :: Developers
|
|
12
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
13
|
+
Classifier: Programming Language :: Python :: 3
|
|
14
|
+
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
|
|
15
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
16
|
+
Requires-Python: >=3.9
|
|
17
|
+
Description-Content-Type: text/markdown
|
|
18
|
+
|
|
19
|
+
# ASRKit
|
|
20
|
+
|
|
21
|
+
**One interface to run and compare any speech-to-text model — local & cloud.**
|
|
22
|
+
|
|
23
|
+
一套接口，跑遍端云所有语音识别。
|
|
24
|
+
|
|
25
|
+
> ⚠️ **Placeholder release.** This `0.0.1` reserves the name while ASRKit is
|
|
26
|
+
> under active development. It does not yet provide functionality.
|
|
27
|
+
> Watch [github.com/asrkit/asrkit](https://github.com/asrkit/asrkit) for the first working release.
|
|
28
|
+
|
|
29
|
+
## What ASRKit will be
|
|
30
|
+
|
|
31
|
+
ASRKit is the Ollama + LiteLLM for speech recognition:
|
|
32
|
+
|
|
33
|
+
- **Local models, `pull` and go** — run open-source ASR models (SenseVoice, Paraformer, Zipformer, Whisper, Moonshine, Parakeet …) with one command, models downloaded on demand.
|
|
34
|
+
- **Cloud APIs, one string away** — call hosted ASR (Volcengine, DashScope, OpenAI, Deepgram …) through the exact same interface, bring your own key.
|
|
35
|
+
- **One protocol across edge and cloud** — a single contract, an OpenAI-compatible endpoint, and a built-in `bench` to compare them all on the same ruler.
|
|
36
|
+
|
|
37
|
+
Apache-2.0. Your audio and keys never pass through us — ASRKit runs on your machine.
|
|
@@ -0,0 +1,4 @@
|
|
|
1
|
+
asrkit/__init__.py,sha256=zEhUPB7YaBDG6lZaKlXZogcX9L_JjbyGqgcqws4VWSo,254
|
|
2
|
+
asrkit-0.0.1.dist-info/METADATA,sha256=28KqRaHym5ylyMPh1EPdnKxIMHgkoRytpJ2rQCstnmk,1805
|
|
3
|
+
asrkit-0.0.1.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
|
|
4
|
+
asrkit-0.0.1.dist-info/RECORD,,
|