GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
hhim8826
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
hhim8826
Model Tree
Qwen/Qwen3-ASR-1.7B-hf
Input Modalities
Output Modalities
Supported Functionality
target_modules 只涵蓋 language_model 的
q_proj / k_proj / v_proj / o_proj,不含 audio_towerpython
import torchfrom peft import PeftModelfrom transformers import AutoProcessor, AutoModelForMultimodalLMbase_model_id = "Qwen/Qwen3-ASR-1.7B-hf"adapter_id = "hhim8826/qwen3-asr-lora-ja-anime"processor = AutoProcessor.from_pretrained(adapter_id)model = AutoModelForMultimodalLM.from_pretrained(base_model_id, dtype=torch.bfloat16, device_map={"": 0})model = PeftModel.from_pretrained(model, adapter_id)model.eval()inputs = processor.apply_transcription_request(audio="path/to/audio.wav", language="Japanese")inputs = {k: v.to(model.device) for k, v in inputs.items()}with torch.autocast(device_type="cuda", dtype=torch.bfloat16):generated = model.generate(**inputs, max_new_tokens=200, repetition_penalty=1.3, no_repeat_ngram_size=3)text = processor.tokenizer.decode(generated[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(text.split("<asr_text>", 1)[-1].strip())
repetition_penalty 與 no_repeat_ngram_size 使用(見上方範例)。訓練資料集 japanese-anime-speech-v2-split 的授權為 GPL,使用或散布本 adapter 前請自行確認授權相容性。