---
language:
- en
- zh
license: apache-2.0
pipeline_tag: audio-classification
tags:
- Language Identification
- LID
- Audio Classification
- VoxLingua107
- audio
- automatic-speech-recognition
- asr
---

<div align="center">
<h1>
FireRedASR2S - FireRedLID
<br>
A SOTA Industrial-Grade Spoken Language Identification System
</h1>

</div>

[[Paper]](https://huggingface.co/papers/2603.10420)
[[Code]](https://github.com/FireRedTeam/FireRedASR2S)
[[Blog]](https://fireredteam.github.io/demos/firered_asr/)
[[Demo]](https://huggingface.co/spaces/FireRedTeam/FireRedASR)


FireRedLID is the Spoken Language Identification (LID) module of **FireRedASR2S**, a state-of-the-art (SOTA), industrial-grade, all-in-one ASR system. It supports 100+ languages and 20+ Chinese dialects/accents, achieving 97.18% accuracy on the FLEURS benchmark, outperforming Whisper and SpeechBrain-LID.

This model was introduced in the paper [FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System](https://huggingface.co/papers/2603.10420).

## 🔥 News
- [2026.02.12] We release FireRedASR2S (FireRedASR2-AED, FireRedVAD, FireRedLID, and FireRedPunc) with model weights and inference code.

## Evaluation
### FireRedLID
Metric: Utterance-level LID Accuracy (%). Higher is better.

|Testset\Model|Languages|FireRedLID|Whisper|SpeechBrain|Dolphin|
|:-----------------:|:---------:|:---------:|:-----:|:---------:|:-----:|
|FLEURS test         |82 languages |**97.18**     |79.41  |92.91      |-|
|CommonVoice test    |74 languages |**92.07**    |80.81  |78.75      |-|
|KeSpeech + MagicData|20+ Chinese dialects/accents |**88.47**     |-|-|69.01|


## Sample Usage

To use this module independently, first clone the [GitHub repository](https://github.com/FireRedTeam/FireRedASR2S) and install the dependencies.

### Python API Usage
```python
from fireredasr2s.fireredlid import FireRedLid, FireRedLidConfig

batch_uttid = ["hello_zh", "hello_en"]
batch_wav_path = ["assets/hello_zh.wav", "assets/hello_en.wav"]

config = FireRedLidConfig(use_gpu=True, use_half=False)
model = FireRedLid.from_pretrained("FireRedTeam/FireRedLID", config)

results = model.process(batch_uttid, batch_wav_path)
print(results)
# [{'uttid': 'hello_zh', 'lang': 'zh mandarin', 'confidence': 0.996, 'dur_s': 2.32, 'rtf': '0.0741', 'wav': 'assets/hello_zh.wav'}, {'uttid': 'hello_en', 'lang': 'en', 'confidence': 0.996, 'dur_s': 2.24, 'rtf': '0.0741', 'wav': 'assets/hello_en.wav'}]
```

## Citation
```bibtex
@article{xu2026fireredasr2s,
  title={FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System},
  author={Xu, Kaituo and Jia, Yan and Huang, Kai and Chen, Junjie and Li, Wenpeng and Liu, Kun and Xie, Feng-Long and Tang, Xu and Hu, Yao},
  journal={arXiv preprint arXiv:2603.10420},
  year={2026}
}
```