GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jaykwok
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
jaykwok
Model Tree
Qwen/Qwen3-ASR-0.6B-hf
Input Modalities
Output Modalities
Supported Functionality
-hf RepositoryThe source repository is intended for the qwen-asr wrapper / original Qwen3-ASR
layout. This repository is intended for native Hugging Face Transformers loading.
The conversion keeps the fine-tuned weights unchanged and only rewrites the
repository layout to match Qwen/Qwen3-ASR-0.6B-hf:
-hf template.thinker.audio_tower.* -> model.audio_tower.*thinker.audio_tower.proj1.* -> model.multi_modal_projector.linear_1.*thinker.audio_tower.proj2.* -> model.multi_modal_projector.linear_2.*thinker.model.* -> model.language_model.*611.1564852224.Requires the stable transformers >= 5.13.0 release for native Qwen3-ASR support:
bash
pip install "transformers>=5.13.0"With uv:
bash
uv pip install "transformers>=5.13.0"python
from transformers import AutoModelForMultimodalLM, AutoProcessor model_id = "jaykwok/Qwen3-ASR-0.6B-JA-Anime-Galgame-hf" processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForMultimodalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto",) inputs = processor.apply_transcription_request( audio="path/to/audio.wav", language="Japanese",).to(model.device, model.dtype) output_ids = model.generate(**inputs, max_new_tokens=256)generated_ids = output_ids[:, inputs["input_ids"].shape[1]:]text = processor.decode(generated_ids, return_format="transcription_only")[0]print(text)chat_template.jinja gained an assistant-role rendering
block, copied verbatim from the base Qwen/Qwen3-ASR-1.7B-hf /
Qwen/Qwen3-ASR-0.6B-hf template (both are byte-identical). transformers
5.15.0 changed Qwen3ASRProcessor.apply_transcription_request()'s language
forcing from a system-prompt string + add_generation_prompt=True to an
assistant-turn prefill ("language <NAME><asr_text>") +
continue_final_message=True (upstream commit c7f9c881). This
repository's template previously had no branch for assistant-role
messages at all, so continue_final_message raised
text
ValueError("continue_final_message is set but the final message does not appear in the chat...")transformers>=5.15.0. The fix is purely additive: the existing
/ rendering and the branch are
unchanged, so callers still on see no behavior
change.This repository was produced with:
powershell
uv run python -m tools.asr.convert_qwen3_asr_to_hf ` --source-model-dir models/jaykwok-Qwen3-ASR-0.6B-JA-Anime-Galgame ` --output-dir agents/temp/20260630_131549_qwen3_asr_0p6b_hf_conversion ` --template-repo Qwen/Qwen3-ASR-0.6B-hf ` --max-shard-size 768MBThis model is specialized for Japanese anime / galgame style speech. It should be evaluated on your own data before production use.
uv run python -m tools.asr.convert_qwen3_asr_to_hf ` --source-model-dir models/jaykwok-Qwen3-ASR-0.6B-JA-Anime-Galgame ` --output-dir agents/temp/20260630_131549_qwen3_asr_0p6b_hf_conversion ` --template-repo Qwen/Qwen3-ASR-0.6B-hf ` --max-shard-size 768MBsystemuseradd_generation_prompttransformers<5.15.0