GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wujunjiehhs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
wujunjiehhs
Model Tree
zhifeixie/Audio-Reasoner
Input Modalities
Output Modalities
Supported Functionality
| Item | Value |
|---|---|
| Model type | Audio-language conditional generation |
| Architecture | Qwen2AudioForConditionalGeneration |
| Parameters | 8.40B |
| Weight format | BF16 Safetensors (4 shards) |
| Context length | 8,192 text positions |
| Base checkpoint | zhifeixie/Audio-Reasoner |
| Post-training | GRPO reinforcement learning |
The model is designed for research involving:
For restoration tasks, prompts should explicitly provide the available operations and request a decision for every operation. A useful output contract is:
text
<THINK>Analyze the audio and evaluate every candidate operation.</THINK> **Detected Audio Issues:**- ... **Restoration Sequences Analysis:**1. denoise(...) - Decision: APPLY / SKIP - Reason: ... **Selected Restoration Pipeline:**1. ...Install the runtime dependencies:
bash
pip install "transformers>=4.57.0" accelerate librosa soundfileRun inference on a local audio file:
python
import librosaimport torchfrom transformers import AutoProcessor, Qwen2AudioForConditionalGeneration model_id = "wujunjiehhs/strixAE"audio_path = "example.wav" processor = AutoProcessor.from_pretrained(model_id)model = Qwen2AudioForConditionalGeneration.from_pretrained( model_id, torch_dtype="auto", device_map="auto",) conversation = [ { "role": "system", "content": ( "You are an audio reasoning assistant. Analyze the audio carefully " "and provide a clear, structured answer." ), }, { "role": "user", "content": [ {"type": "audio", "audio": audio_path}, { "type": "text", "text": ( "Identify the audio issues. Evaluate denoising, dereverberation, " "source separation, and super-resolution. For each operation, " "return APPLY or SKIP with a reason, then propose an ordered pipeline." ), }, ], },] prompt = processor.apply_chat_template( conversation, add_generation_prompt=True, tokenize=False,)audio, _ = librosa.load( audio_path, sr=processor.feature_extractor.sampling_rate, mono=True,)inputs = processor( text=prompt, audio=audio, sampling_rate=processor.feature_extractor.sampling_rate, return_tensors="pt", padding=True,)inputs = {k: v.to(model.device) for k, v in inputs.items()} with torch.inference_mode(): generated_ids = model.generate(**inputs, max_new_tokens=1024) generated_ids = generated_ids[:, inputs["input_ids"].shape[1]:]response = processor.batch_decode( generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(response)The repository includes its chat template, tokenizer, processor configuration, generation configuration, and merged model weights; no adapter merge is required at inference time.
This checkpoint was produced by GRPO post-training and then merged for deployment. Exact training data composition, reward functions, hyperparameters, compute, and checkpoint-selection criteria are not included in this release. Users should not assume that benchmark numbers reported for the upstream Audio-Reasoner checkpoint transfer unchanged to this model.
strixAE 是在 Audio-Reasoner 基础上进行 GRPO 强化学习得到的音频理解代理。它面向音频理解、音质问题分析、候选修复操作的 APPLY/SKIP 判断，以及修复流程排序。当前仓库尚未发布该 GRPO 检查点的独立评测结果，建议在实际数据上验证后再部署。
This work builds on Audio-Reasoner and Qwen2-Audio. Please cite the upstream Audio-Reasoner work when using this checkpoint:
bibtex
@misc{xie2025audioreasonerimprovingreasoningcapability, title = {Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models}, author = {Zhifei Xie and Mingbao Lin and Zihang Liu and Pengcheng Wu and Shuicheng Yan and Chunyan Miao}, year = {2025}, eprint = {2503.02318}, archivePrefix= {arXiv}, primaryClass = {cs.SD}, url = {https://arxiv.org/abs/2503.02318}}This release follows the MIT license included with the upstream Audio-Reasoner project. Users are responsible for reviewing and complying with the terms of all upstream models, datasets, and dependencies.
<THINK>Analyze the audio and evaluate every candidate operation.</THINK>**Detected Audio Issues:**- ...**Restoration Sequences Analysis:**1. denoise(...) - Decision: APPLY / SKIP - Reason: ...**Selected Restoration Pipeline:**1. ...pip install "transformers>=4.57.0" accelerate librosa soundfileimport librosaimport torchfrom transformers import AutoProcessor, Qwen2AudioForConditionalGeneration model_id = "wujunjiehhs/strixAE"audio_path = "example.wav" processor = AutoProcessor.from_pretrained(model_id)model = Qwen2AudioForConditionalGeneration.from_pretrained( model_id, torch_dtype="auto", device_map="auto",) conversation = [ { "role": "system", "content": ( "You are an audio reasoning assistant. Analyze the audio carefully " "and provide a clear, structured answer." ), }, { "role": "user", "content": [ {"type": "audio", "audio": audio_path}, { "type": "text", "text": ( "Identify the audio issues. Evaluate denoising, dereverberation, " "source separation, and super-resolution. For each operation, " "return APPLY or SKIP with a reason, then propose an ordered pipeline." ), }, ], },] prompt = processor.apply_chat_template( conversation, add_generation_prompt=True, tokenize=False,)audio, _ = librosa.load( audio_path, sr=processor.feature_extractor.sampling_rate, mono=True,)inputs = processor( text=prompt, audio=audio, sampling_rate=processor.feature_extractor.sampling_rate, return_tensors="pt", padding=True,)inputs = {k: v.to(model.device) for k, v in inputs.items()} with torch.inference_mode(): generated_ids = model.generate(**inputs, max_new_tokens=1024) generated_ids = generated_ids[:, inputs["input_ids"].shape[1]:]response = processor.batch_decode( generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(response)@misc{xie2025audioreasonerimprovingreasoningcapability, title = {Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models}, author = {Zhifei Xie and Mingbao Lin and Zihang Liu and Pengcheng Wu and Shuicheng Yan and Chunyan Miao}, year = {2025}, eprint = {2503.02318}, archivePrefix= {arXiv}, primaryClass = {cs.SD}, url = {https://arxiv.org/abs/2503.02318}}