wav2vec2-large-xlsr-japanese-hiragana
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT. When using this model, make sure that your speech input is sampled at 16kHz. The model can be used directly (without a language model) as follows: python !pip install mecab-python3 !pip install unidic-lite !pip install pykakasi !python -m unidic download import torch im...
Params
320 M
Context
—
Downloads 30d
472 K
Likes
11
Download history
daily snapshots · 33 days
▲ 78 K in the last 30 days (14.1%)
550 K472 K
Aug 23Sep 2Sep 12Sep 21
550 K378 K
Aug 20Aug 31Sep 11Sep 21
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
- 86
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2022-03-02
- Training datasets
- common_voice
- Common Voice Japanese (reported)
- 10.99
- Added to our catalog
- 2026-08-20
Compare with any automatic-speech-recognition model