wav2vec2-1b-npsc-nst-bokmaal-repaired
wav2vec2-1b-npsc-nst-bokmaal-repaired (NbAiLab, 2022) is a 1 billion parameter speech-and-audio model. wav2vec2-1b-npsc-nst-bokmaal-repaired is an open-weights audio model with roughly 1 billion parameters.
by NbAiLab · 1B parameters
Best for
- automatic speech recognition
Ways to use wav2vec2-1b-npsc-nst-bokmaal-repaired in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your NbAiLab API key. osFoundry discovers wav2vec2-1b-npsc-nst-bokmaal-repaired automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
wav2vec2-1b-npsc-nst-bokmaal-repaired is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run wav2vec2-1b-npsc-nst-bokmaal-repaired
wav2vec2-1b-npsc-nst-bokmaal-repaired runs on a single 16GB consumer GPU (~1 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~3 GB).
wav2vec2-1b-npsc-nst-bokmaal-repaired vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about wav2vec2-1b-npsc-nst-bokmaal-repaired
Is wav2vec2-1b-npsc-nst-bokmaal-repaired free to use?
wav2vec2-1b-npsc-nst-bokmaal-repaired is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use wav2vec2-1b-npsc-nst-bokmaal-repaired commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does wav2vec2-1b-npsc-nst-bokmaal-repaired need?
Approximately 1 GB at Q4 quantisation, or 3 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run wav2vec2-1b-npsc-nst-bokmaal-repaired locally?
Yes. wav2vec2-1b-npsc-nst-bokmaal-repaired is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is wav2vec2-1b-npsc-nst-bokmaal-repaired best at?
wav2vec2-1b-npsc-nst-bokmaal-repaired is well-suited to automatic speech recognition.
How do I use wav2vec2-1b-npsc-nst-bokmaal-repaired in osFoundry?
Paste your NbAiLab API key in the key dialog (or deploy the open weights for self-hostable models), assign wav2vec2-1b-npsc-nst-bokmaal-repaired to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by NbAiLab on July 26, 2022. Source: https://huggingface.co/NbAiLab/wav2vec2-1b-npsc-nst-bokmaal-repaired