---
library_name: transformers
tags:
- automatic-speech-recognition
license: apache-2.0
datasets:
- reazon-research/reazonspeech
language:
- ja
metrics:
- cer
base_model:
- reazon-research/japanese-wav2vec2-large
---

# `japanese-wav2vec2-large-rs35kh`

This model is a [wav2vec 2.0 Large](https://huggingface.co/reazon-research/japanese-wav2vec2-large) fine-tuned on the large-scale Japanese ASR corpus [ReazonSpeech v2.0](https://huggingface.co/datasets/reazon-research/reazonspeech).

## Usage

You can use this model through `transformers` library:
```python
import librosa
import numpy as np
from transformers import AutoProcessor, Wav2Vec2ForCTC

model = Wav2Vec2ForCTC.from_pretrained(
    "reazon-research/japanese-wav2vec2-large-rs35kh",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
).to("cuda")
processor = AutoProcessor.from_pretrained("reazon-research/japanese-wav2vec2-large-rs35kh")

audio, _ = librosa.load(audio_filepath, sr=16_000)
audio = np.pad(audio, pad_width=int(0.5 * 16_000))  # Recommend to pad audio before inference
input_values = processor(
    audio,
    return_tensors="pt",
    sampling_rate=16_000
).input_values.to("cuda").to(torch.bfloat16)

with torch.inference_mode():
    logits = model(input_values).logits.cpu()
predicted_ids = torch.argmax(logits, dim=-1)[0]
transcription = processor.decode(predicted_ids, skip_special_tokens=True)
```

## Test Results

We report the Character Error Rate (CER) of our model and the other wav2vec2 families.
| Model                                           | #Prameters⬇ |  AVERAGE⬇  | JSUT-BASIC5000⬇ | Common Voice⬇ | TEDxJP-10K⬇ |
| :---------------------------------------------- | :---------: | :--------: | :-------------: | :-----------: | :---------: |
| reazon-research/japanese-wav2vec2-large-rs35kh  |    319M     | **16.25%** |     11.00%      |    18.23%     | **19.53%**  |
| reazon-research/japanese-wav2vec2-base-rs35kh   |    96.7M    |   20.40%   |     13.22%      |    23.76%     |   24.23%    |
| Ivydata/wav2vec2-large-xlsr-53-japanese         |    318M     |   24.23%   |     13.83%      |  **18.15%**   |   40.72%    |
| jonatasgrosman/wav2vec2-large-xlsr-53-japanese  |    317M     |   31.82%   |      4.25%      |    40.58%     |   50.63%    |
| vumichien/wav2vec2-large-xlsr-japanese          |    318M     |   39.87%   |    **4.21%**    |    53.29%     |   62.12%    |

We also report the CER for long-form speech.
| Model                                           | #Prameters⬇ | JSUT-BOOK⬇ |
| :---------------------------------------------- | :---------: | :--------: |
| reazon-research/japanese-wav2vec2-large-rs35kh  |    319M     | **30.98%** |
| reazon-research/japanese-wav2vec2-base-rs35kh   |    96.7M    |   82.84%   |
| Ivydata/wav2vec2-large-xlsr-53-japanese         |    318M     |   65.60%   |
| jonatasgrosman/wav2vec2-large-xlsr-53-japanese  |    317M     |   46.20%   |
| vumichien/wav2vec2-large-xlsr-japanese          |    318M     |   46.52%   |

## Citation
```bibtex
@misc{reazon-research-japanese-wav2vec2-large-rs35kh,
  title={japanese-wav2vec2-large-rs35kh},
  author={Sasaki, Yuta},
  url = {https://huggingface.co/reazon-research/japanese-wav2vec2-large-rs35kh},
  year = {2024}
}
```

## License

[Apaceh Licence 2.0](https://choosealicense.com/licenses/apache-2.0/)