Downloads · 30 days
42
7% of all-time downloads
jaykwok/Qwen3-ASR-0.6B-JA-Anime-Galgame-hf
Qwen3-ASR-0.6B-JA-Anime-Galgame-hf is a automatic speech recognition model from jaykwok. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This is a Transformers-native -hf layout conversion of jaykwok/Qwen3-ASR-0.6B-JA-Anime-Galgame, which was fine-tuned from the non--hf Qwen3-ASR checkpoint.
Downloads · 30 days
42
7% of all-time downloads
All-time downloads
621
Public
Parameters
782M
1.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.6 GB · 99%
From the Hugging Face model README
This is a Transformers-native -hf layout conversion of
jaykwok/Qwen3-ASR-0.6B-JA-Anime-Galgame,
which was fine-tuned from the non--hf Qwen3-ASR checkpoint.
-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:
pip install "transformers>=5.13.0"
With uv:
uv pip install "transformers>=5.13.0"
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
ValueError("continue_final_message is set but the final message does not appear in the chat...") on every transcription request under
transformers>=5.15.0. The fix is purely additive: the existing
system/user rendering and the add_generation_prompt branch are
unchanged, so callers still on transformers<5.15.0 see no behavior
change.This repository was produced with:
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 768MB
This model is specialized for Japanese anime / galgame style speech. It should be evaluated on your own data before production use.