sskorol/vosk-api-gpu

Vosk ASR Docker images with GPU for Jetson boards, PCs, M1 laptops and GPC

38
/ 100
Emerging

This project provides pre-configured packages for Vosk, an open-source speech-to-text engine, optimized for NVIDIA GPUs on various hardware like Jetson boards, PCs, and Google Cloud. It takes audio recordings (like WAV files) and converts them into text transcripts, making it easier for users to integrate voice recognition into their applications without complex setup. This is ideal for developers, engineers, and researchers working on applications that need efficient, local audio transcription.

No commits in the last 6 months.

Use this if you need to build or run a high-performance speech-to-text application on NVIDIA GPU-enabled hardware or Google Cloud, and want to simplify the setup of Vosk with Docker.

Not ideal if you don't have access to NVIDIA GPU hardware, prefer a cloud-based speech-to-text API, or only need basic, non-optimized transcription on a CPU.

speech-to-text voice-recognition audio-transcription edge-ai cloud-ml
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

45

Forks

7

Language

Shell

License

Apache-2.0

Last pushed

May 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sskorol/vosk-api-gpu"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.