wav2vec2-live and wav2asr

One tool provides a live speech recognition application utilizing Wav2vec 2.0, while the other offers a library-level implementation of the Wav2vec 2.0 framework for ASR tasks, making them ecosystem siblings where the library could serve as a foundational component for building applications like the live one.

wav2vec2-live
46
Emerging
wav2asr
27
Experimental
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 20/25
Maintenance 0/25
Adoption 3/25
Maturity 9/25
Community 15/25
Stars: 378
Forks: 58
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 4
Forks: 4
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About wav2vec2-live

oliverguhr/wav2vec2-live

A live speech recognition using Facebooks wav2vec 2.0 model.

Provides real-time streaming speech recognition by continuously processing microphone input through any wav2vec2 model from Hugging Face, with configurable audio devices and per-inference timing metrics. The architecture uses PyAudio for live audio capture and runs inference asynchronously, returning recognized text alongside processing latency and sample duration for performance monitoring.

About wav2asr

phanxuanphucnd/wav2asr

A library version of wav2vec 2.0 framework for Automatic Speech Recognition task.

Scores updated daily from GitHub, PyPI, and npm data. How scores work