---
title: FireRedASR-AED-L
canonical_url: "https://www.modelscope.cn/models/pengzhendong/FireRedASR-AED-L"
md_url: "https://www.modelscope.cn/models/pengzhendong/FireRedASR-AED-L.md"
repository: pengzhendong/FireRedASR-AED-L
last_updated: 2025-02-05
license: apache-2.0
pipeline_tag: auto-speech-recognition
tasks:
  - auto-speech-recognition
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 72873
stars: 9
---

# FireRedASR-AED-L

> FireRedASR-AED-L - pengzhendong 在 ModelScope 开源的模型。FireRedASR is a family of large-scale automatic speech recognition (ASR) models supporting Mandarin, Chinese dialects and English, while also offering singing lyrics recognition capability, achieving a new…

pengzhendong/FireRedASR-AED-L 是 ModelScope 魔搭社区上的auto-speech-recognition模型，采用 apache-2.0 许可。

- **Repository**: pengzhendong/FireRedASR-AED-L
- **License**: apache-2.0
- **Tasks**: auto-speech-recognition
- **Downloads**: 72873
- **Stars**: 9
- **Last updated**: 2025-02-05

Source: https://www.modelscope.cn/models/pengzhendong/FireRedASR-AED-L

---

FireRedASR is a family of large-scale automatic speech recognition (ASR) models supporting Mandarin, Chinese dialects and English, while also offering singing lyrics recognition capability, achieving a new state-of-the-art on public Mandarin ASR benchmarks.

FireRedASR is designed to meet diverse requirements in superior performance and optimal efficiency across various applications. It comprises two variants:
- FireRedASR-LLM: Designed to achieve state-of-the-art (SOTA) performance and to enable seamless end-to-end speech interaction. It adopts an Encoder-Adapter-LLM framework leveraging large language model (LLM) capabilities.
- FireRedASR-AED: Designed to balance high performance and computational efficiency and to serve as an effective speech representation module in LLM-based speech models. It utilizes an Attention-based Encoder-Decoder (AED) architecture.