---
title: japanese-data2vec-audio-base
canonical_url: "https://www.modelscope.cn/models/rinna/japanese-data2vec-audio-base"
md_url: "https://www.modelscope.cn/models/rinna/japanese-data2vec-audio-base.md"
repository: rinna/japanese-data2vec-audio-base
last_updated: 2025-10-10
license: apache-2.0
pipeline_tag: feature-extraction
tasks:
  - feature-extraction
model_type:
  - data2vec-audio
architectures:
  - Data2VecAudioModel
parameters: 93.2M
tensor_type:
  - F32
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ja
downloads: 33
stars: 0
tags:
  - data2vec
  - speech
---

# japanese-data2vec-audio-base

> japanese-data2vec-audio-base - rinna 在 ModelScope 开源的模型。rinna/japanese-data2vec-audio-base

rinna/japanese-data2vec-audio-base 是 ModelScope 魔搭社区上的 93.2M 参数feature-extraction模型，采用 apache-2.0 许可。

- **Repository**: rinna/japanese-data2vec-audio-base
- **License**: apache-2.0
- **Tasks**: feature-extraction
- **Parameters**: 93.2M
- **Tags**: data2vec, speech
- **Downloads**: 33
- **Stars**: 0
- **Last updated**: 2025-10-10

Source: https://www.modelscope.cn/models/rinna/japanese-data2vec-audio-base

---

# `rinna/japanese-data2vec-audio-base`

![rinna-icon](./rinna.png)

# Overview

This is a Japanese data2vec Audio Base model trained by [rinna Co., Ltd.](https://rinna.co.jp/)

* **Model summary**

  The model architecture is the same as the [original data2vec Audio Base model](https://huggingface.co/facebook/data2vec-audio-base), which contains 12 transformer layers with 12 attention heads.
  The model was trained using code from the [official repository](https://github.com/facebookresearch/fairseq/tree/main/examples/data2vec#data2vec), and the detailed training configuration can be found in the same repository and the [original paper](https://ai.meta.com/research/data2vec-a-general-framework-for-self-supervised-learning-in-speech-vision-and-language/).


* **Training**

  The model was trained on approximately 19,000 hours of following Japanese speech corpus ReazonSpeech v1.
  - [ReazonSpeech](https://huggingface.co/datasets/reazon-research/reazonspeech)

* **Contributors**

  - [Yukiya Hono](https://huggingface.co/yky-h)
  - [Kentaro Mitsui](https://huggingface.co/Kentaro321)
  - [Kei Sawada](https://huggingface.co/keisawada)
    
* **Release date**

    March 7, 2024

---

# How to use the model

```python
import soundfile as sf
from transformers import AutoFeatureExtractor, AutoModel

model_name = "rinna/japanese-data2vec-audio-base"
feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)
model.eval()

raw_speech_16kHz, sr = sf.read(audio_file)
inputs = feature_extractor(
    raw_speech_16kHz,
    return_tensors="pt",
    sampling_rate=sr,
)
outputs = model(**inputs)

print(f"Input:  {inputs.input_values.size()}")  # [1, #samples]
print(f"Output: {outputs.last_hidden_state.size()}")  # [1, #frames, 768]
```

A fairseq checkpoint file can also be available [here](https://huggingface.co/rinna/japanese-data2vec-audio-base/tree/main/fairseq).

---

# How to cite
```bibtex
@misc{rinna-japanese-data2vec-audio-base,
    title = {rinna/japanese-data2vec-audio-base},
    author = {Hono, Yukiya and Mitsui, Kentaro and Sawada, Kei},
    url = {https://huggingface.co/rinna/japanese-data2vec-audio-base}
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}
```

---

# References
```bibtex
@inproceedings{baevski2022data2vec,
    title={Data2vec: A general framework for self-supervised learning in speech, vision and language},
    author={Baevski, Alexei and Hsu, Wei-Ning and Xu, Qiantong and Babu, Arun and Gu, Jiatao and Auli, Michael},
    booktitle={International Conference on Machine Learning},
    year={2022},
    pages={1298--1312},
    doi={10.48550/arXiv.2202.03555}
}
```
---

# License
[The Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0)