Model reference · open weights
wav2vec2-large-voxrex-swedish is an open-weight audio or speech model from KBLab, 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
Wav2vec 2.0 large VoxRex Swedish (C) Finetuned version of KBs VoxRex large model using Swedish radio broadcasts, NST and Common Voice data. Evalutation without a language model gives the following: WER for NST + Common Voice test set (2% of total sentences) is 2.5%. WER for Common Voice test set is 8.49% directly and 7.37% with a 4-gram language model. When using this model, make sure that your speech input is sampled at 16kHz. Update 2022-01-10: Updated to VoxRex-C version. Update 2022-05-16: Paper is is here. Performance\ Training This model has been fine-tuned for 120000 updates on NST + CommonVoice<del and then for an additional 20000 updates on CommonVoice only. The additional fine-tuning on CommonVoice hurts performance on the NST+CommonVoice test set somewhat and, unsurprisingly, improves it on the CommonVoice test set. It seems to perform generally better though [citation needed]</del. Usage The model can be used directly (without a language model) as follows: Citation https://arxiv.org/abs/2205.03026
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | KBLab |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 315M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 1.5M downloads / month |
| Likes | 13 |
| 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-voxrex-swedish | 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 |
|---|---|---|---|
| Speech Recognition | Common Voice | Test WER | 8.49 |
Using it via the API
Once AxForge deploys wav2vec2-large-voxrex-swedish for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-voxrex-swedish 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-voxrex-swedish" -F file=@audio.mp3
Licence
Open weights under cc0-1.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗