FireRedASR2 LLM
FireRedTeam's LLM-backbone Mandarin-first bilingual ASR — 8B+ parameters engineered for state-of-the-art Chinese and dialect accuracy
Opens the desktop app and downloads this model for you.
Don't have the app yet? Download OpenASR Desktop
let's line up this week's release plan,
the beta build can ship on Friday,
then loop in design and QA,
Why it fits
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.
What you can do with it
- 🥇 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)
Other models
Developer details CLI commands, file hashes, and per-quant downloads — for scripting and verification.
Model facts
Usage
These are CLI / local-server examples. The desktop app runs this model without typing a command — use Install above.
$ 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)