Model reference · open weights
wav2vec2-large-xlsr-korean is an open-weight audio or speech model from kresnik, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Evaluation on Zeroth-Korean ASR corpus Google colab notebook(Korean) Expected WER: 4.74% Expected CER: 1.78%
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | kresnik |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 317M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 999k downloads / month |
| Likes | 56 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| wav2vec2-large-xlsr-korean | 317M | BF16 | ~0.7 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | Zeroth Korean | Test WER | 4.74 |
| Automatic Speech Recognition | Zeroth Korean | Test CER | 1.78 |
Using it via the API
Once AxForge deploys wav2vec2-large-xlsr-korean for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-korean below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="wav2vec2-large-xlsr-korean" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗