cverse-asr-inference-adapter v0.1.0

adapter

capsule://quake0day/[email protected]

Provides adapters for various Automatic Speech Recognition (ASR) models, allowing the core inference service to use different ASR providers (e.g., Qwen ASR, Whisper) through a unified interface.

Owns

Base ASR plugin interface
Specific ASR model implementations (e.g., Qwen, Whisper)

Does not own

The core inference service
Other AI model types (LLM, TTS, Avatar, etc.)

AI orientation

An AI agent working on this capsule would focus on adding new ASR model integrations, improving existing ASR model performance, or optimizing the ASR plugin's interaction with external APIs. It requires knowledge of ASR technologies and Python plugin development.

Avoid

Modifying the core inference service or other AI model types.

Provides

library:asr-plugin — ASR model implementations conforming to the inference core's plugin interface.

Dependencies

Capsules

cverse-inference-core >=0.1.0

Invariants (must always hold)

ASR plugins must correctly transcribe audio inputs.
Plugins must adhere to the defined ASR plugin interface.

Source files (4)

Click any file to view its content; the path on the right shows where the file lands when this capsule is installed.

src/inference/plugins/asr/__init__.py → plugins/asr/__init__.py
src/inference/plugins/asr/base.py → plugins/asr/base.py
src/inference/plugins/asr/qwen_asr_plugin.py → plugins/asr/qwen_asr_plugin.py
src/inference/plugins/asr/whisper_plugin.py → plugins/asr/whisper_plugin.py

Plus capsule.yaml and install.json.

Upstream source

https://github.com/quake0day/cyberverse-capsules/blob/main/cverse-asr-inference-adapter/capsule.yaml

Pull this capsule locally:

capsule pull capsule://quake0day/[email protected]

Or render to your terminal:

capsule man capsule://quake0day/[email protected]