w2v-bert-2.0
We are open-sourcing our Conformer-based W2v-BERT 2.0 speech encoder as described in Section 3.2.1 of the paper, which is at the core of our Seamless models.
Params
580 M
Context
—
Downloads 30d
2.2 M
Likes
231
Download history
daily snapshots · 55 days
▲ 213 K in the last 30 days (10.8%)
2.4 M2.0 M
Aug 22Sep 1Sep 11Sep 20
2.4 M1.3 M
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 | 2.3 GB | 3.1 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
- Wav2Vec2BertModel
- Parameters
- 580 M
- Tensor type
- F32
- Layers / heads
- 24 / 16
- Licence
- mit
- First seen on the Hub
- 2023-12-19
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any feature-extraction model