FireRedASR2 LLM
FireRedTeam's LLM-backbone Mandarin-first bilingual ASR — 8B+ parameters engineered for state-of-the-art Chinese and dialect accuracy
我们先对一下这周的发布节奏，
beta 版本可以安排在周五，
然后同步给 design 和 QA，
为什么适合你
FireRedASR2-LLM is the Encoder-Adapter-LLM member of FireRedASR2, the successor to
FireRedTeam's open-source industrial-grade FireRedASR speech-recognition family, released as
part of the FireRedASR2S all-in-one ASR system. At 8B+ parameters with an LLM-scale decoder
backbone, it is the bigger and more accurate sibling of the already-available
firered-aed-l-v2 (FireRedASR2-AED, a 1.1B-parameter attention encoder-decoder reporting
3.05%/11.67% avg CER). The FireRedASR2S technical report (arXiv:2603.10420) and the upstream model
card both report 2.89% average Character Error Rate across four public Mandarin benchmarks
and 11.55% average CER across 19 public Chinese dialect/accent benchmarks -- outperforming
Doubao-ASR (3.69%/15.39%), Qwen3-ASR (3.76%/11.85%), and Fun-ASR (4.16%/12.76%) on the paper's own
comparison table. These numbers belong to FireRedASR2-LLM and should not be confused with the
smaller firered-aed-l-v2's 3.05%/11.67% figures. The model is bilingual (Mandarin Chinese and
English). This OpenASR pack distributes the q4_k quantization build, repackaged as an .oasr
pack that runs natively in the OpenASR runtime -- fully local, no Python at inference time, no
cloud upload. Licensed under Apache-2.0, inherited from the upstream release.
你可以用它做什么
- 🥇 Best-in-class Mandarin accuracy — 2.89% average CER across four public Mandarin benchmarks, outperforming Doubao-ASR (3.69%), Qwen3-ASR (3.76%), and Fun-ASR (4.16%) on the same comparison table (arXiv:2603.10420; FireRedTeam's FireRedASR2-LLM model card)
- 🗣️ Leading dialect and accent coverage — 11.55% average CER across 19 public Chinese dialect/accent benchmarks, ahead of Doubao-ASR (15.39%) and Qwen3-ASR (11.85%) (arXiv:2603.10420; FireRedTeam's FireRedASR2-LLM model card)
- 🇨🇳🇬🇧 Bilingual Mandarin + English — one 8B+ parameter checkpoint handles both languages, as demonstrated in the upstream model card's bilingual examples (FireRedTeam's FireRedASR2-LLM model card)
- 🧠 LLM-scale decoder backbone — Encoder-Adapter-LLM architecture at 8B+ parameters, the bigger and more accurate sibling of the already-available firered-aed-l-v2 (1.1B AED, 3.05%/11.67% avg CER) (FireRedTeam's FireRedASR2-LLM model card)
- 🔒 Fully local, q4_k build — runs 100% on-device via OpenASR's .oasr runtime with no cloud upload, under the Apache-2.0 license inherited from upstream (FireRedTeam's FireRedASR2-LLM model card)
其他模型
开发者详情 CLI 命令、文件哈希和不同量化版本，适合自动化脚本与完整性校验。
模型详细信息
使用方式
以下是 CLI／本地服务端示例。桌面应用无需输入任何命令即可运行此模型——用上方的“安装”即可。
$ openasr pull firered2-llm:q4 ↓ firered2-llm.oasr 4.4 GB ✓ verified sha256 $ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/firered2-llm/q4_k/firered2-llm-q4_k.oasr ✓ local transcript · 0 bytes sent
$ openasr serve --backend native --model-pack ~/.openasr/models/firered2-llm/q4_k/firered2-llm-q4_k.oasr --addr 127.0.0.1:8080 ▶ http://127.0.0.1:8080 · model=firered2-llm · 0 bytes will leave this host
from openai import OpenAI client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local") audio = open("meeting.wav", "rb") text = client.audio.transcriptions.create(model="firered2-llm", file=audio)