wav2vec2-xls-r-300m-hebrew
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the private datasets in 2 stages - firstly was fine-tuned on a small dataset with good samples Then the obtained model was fine-tuned on a large dataset with the small good dataset, with various samples from different sources, and with an unlabeled dataset that was weakly labeled using a previously trained model.
Params
320 M
Context
—
Downloads 30d
1.3 M
Likes
7
Download history
daily snapshots · 55 days
▲ 484 K in the last 30 days (61.3%)
1.5 M799 K
Aug 22Sep 1Sep 11Sep 20
1.5 M607 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
- 32
- Layers / heads
- 24 / 16
- First seen on the Hub
- 2022-03-02
- Training datasets
- undisclosed
- Custom Dataset (reported)
- 23.18
- Added to our catalog
- 2026-07-28
Compare with any automatic-speech-recognition model