nb-wav2vec2-1b-nynorsk
This model is finetuned on top of feature extractor XLS-R from Facebook/Meta. The finetuned model achieves the following results on the test set with a 5-gram KenLM. The numbers in parentheses are the results without the language model: - WER: 0.1132 (0.1364) - CER: 0.0402 (---)
Params
960 M
Context
—
Downloads 30d
1.2 M
Likes
1
Download history
daily snapshots · 55 days
▲ 494 K in the last 30 days (67.0%)
1.4 M735 K
Aug 22Sep 1Sep 11Sep 20
1.4 M556 K
Jul 28Aug 15Sep 2Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 3.9 GB | 4.9 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Wav2Vec2ForCTC
- Parameters
- 960 M
- Tensor type
- F32
- Vocabulary
- 34
- Layers / heads
- 48 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2022-06-09
- Training datasets
- NbAiLab/NPSC
- NPSC (reported)
- 0.04026369658774
- Added to our catalog
- 2026-07-28
Compare with any automatic-speech-recognition model