Model reference · open weights
w2v-xls-r-uk is an open-weight audio or speech model from Yehor, 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
🚨🚨🚨 ATTENTION! 🚨🚨🚨 Use an updated model: https://huggingface.co/Yehor/w2v-bert-uk-v2.1 Community - Discord: https://bit.ly/discord-uds - Speech Recognition: https://t.me/speechrecognitionuk - Speech Synthesis: https://t.me/speechsynthesisuk See other Ukrainian models: https://github.com/egorsmkv/speech-recognition-uk Evaluation results Metrics (float16) using evaluate library with batchsize=1: - WER: 0.2024 metric, 20.24% - CER: 0.0364 metric, 3.64% - Accuracy on words: 79.76% - Accuracy on chars: 96.36% - Inference time: 63.4848 seconds - Audio duration: 16665.5212 seconds - RTF: 0.0038 Cite this work
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Yehor |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 315M |
| Variants | 1 |
| Runs with | transformers |
| Based on | facebook/wav2vec2-xls-r-300m |
| Released | 2022-06-08 |
| Popularity | 803k downloads / month |
| Likes | 8 |
| 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 |
|---|---|---|---|---|---|
| w2v-xls-r-uk | 315M | 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 | common_voice_10_0 | WER | 20.24 |
| Automatic Speech Recognition | common_voice_10_0 | CER | 3.64 |
Using it via the API
Once AxForge deploys w2v-xls-r-uk for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (w2v-xls-r-uk 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="w2v-xls-r-uk" -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 ↗