wav2vec2-large-xlsr-kazakh
Fine-tuned facebook/wav2vec2-large-xlsr-53 for Kazakh ASR using the Kazakh Speech Corpus v1.1
Params
320 M
Context
—
Downloads 30d
525 K
Likes
21
Download history
daily snapshots · 84 days
▲ 140 K in the last 30 days (36.2%)
525 K386 K
Sep 25Oct 5Oct 15Oct 24
525 K366 K
Aug 2Aug 30Sep 27Oct 24
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
- 45
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- kazakh_speech_corpus
- Kazakh Speech Corpus v1.1 (reported)
- 19.65
- Added to our catalog
- 2026-08-02
Compare with any automatic-speech-recognition model