wav2vec2-xls-r-300m-ftspeech
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the FTSpeech dataset, being a dataset of 1,800 hours of transcribed speeches from the Danish parliament.
Params
320 M
Context
—
Downloads 30d
949 K
Likes
0
Download history
daily snapshots · 55 days
▲ 398 K in the last 30 days (72.2%)
1.1 M556 K
Aug 22Sep 1Sep 11Sep 20
1.1 M421 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 | 1.3 GB | 1.9 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
- 320 M
- Tensor type
- F32
- Vocabulary
- 35
- Layers / heads
- 24 / 16
- Licence
- other
- First seen on the Hub
- 2022-03-04
- Training datasets
- ftspeech
- Danish Common Voice 8.0 (reported)
- 17.91
- Alvenir ASR test dataset (reported)
- 13.84
- Added to our catalog
- 2026-07-28
Compare with any automatic-speech-recognition model