Intended Use

This model is intended for Japanese ASR in speech with galgame or anime-like delivery, including:

• visual novel and game voice transcription
• subtitle generation workflows
• Japanese character dialogue with expressive voice acting
• research on domain adaptation from general ASR models to anime-style speech

It is not yet validated as a general-purpose Japanese ASR model. For broad Japanese speech, compare against the original base model before production use.

Training

• Base model: Qwen/Qwen3-ASR-0.6B
• Fine-tuning type: full SFT / full checkpoint fine-tune
• Training dataset: litagin/Galgame_Speech_ASR_16kHz
• Checkpoint step: 29239
• Epoch: 1.0
• Last recorded internal eval loss: 0.1372 at step 29000

The eval loss above comes from the training run's internal evaluation split. It should not be treated as an external benchmark score.

Evaluation

Fixed 800-Clip Benchmark

The following numbers are from a fixed 800-clip Japanese ASR evaluation set sampled with seed 20260531. The set contains 200 clips from each source:

Total: 800 clips, 4108.3s audio, 17354 reference characters.

Metric: strict character error rate (CER) after removing whitespace and common Japanese/ASCII punctuation. S, I, and D are substitution, insertion, and deletion rates divided by reference characters. The same decoding and normalization were used for all models.

CER by source:

For this 0.6B checkpoint, full SFT improves overall CER from 0.1673 to 0.1438, a 14.0% relative reduction. The largest improvement is deletion reduction, from 0.0434 to 0.0249. In-domain gains are stronger: Nekopara CER improves by 17.5% relative, and Anime Speech CER improves by 34.8% relative. Common Voice is effectively flat, so this checkpoint should still be treated primarily as a galgame/anime-domain model rather than a general Japanese ASR upgrade.

These numbers are a small reproducible sanity benchmark, not a comprehensive public leaderboard. Strict character CER can over-penalize kana/kanji variants, long-vowel spelling, expressive writing, and transcript style differences.

Additional Evaluation Candidates

Recommended additional evaluation sets:

• ntaquan0125/steinsgate-voice, a relatively small STEINS;GATE visual novel voice dataset with Japanese audio and text, if access and licensing are acceptable
• grider-transwithai/nekopara-speech, a public visual-novel/game voice dataset with Japanese transcriptions and character metadata
• joujiboi/japanese-anime-speech, a smaller anime/visual-novel ASR dataset than japanese-anime-speech-v2
• makiligon/Blue-Archive-Japanese-Voicelines, a small game voice-line collection; verify that usable transcripts are available before using it for CER
• japanese-asr/ja_asr.common_voice_8_0, a small general Japanese ASR sanity set
• japanese-asr/ja_asr.jsut_basic5000, a compact read-speech Japanese benchmark

For a larger follow-up benchmark, use a fixed sample instead of evaluating every available hour. A practical next pass would be:

Report CER plus substitution, insertion, and deletion rates, with the exact normalization and decoding settings.

Repository Contents

This repository intentionally includes training recovery artifacts:

• model.safetensors
• tokenizer and processor files
• optimizer.pt
• scheduler.pt
• rng_state.pth
• trainer_state.json
• training_args.bin

For inference-only use, the optimizer and scheduler files are not required.

Inference

Use the same inference stack as the upstream Qwen3-ASR models, replacing the model id with:

text
Copy code
jaykwok/Qwen3-ASR-0.6B-JA-Anime-Galgame

Refer to the upstream Qwen3-ASR documentation for the latest supported inference commands and runtime requirements.

Limitations

• The model is specialized for galgame/anime-style Japanese speech and may be less reliable on news, meetings, lectures, or spontaneous conversation.
• The training data may contain adult or NSFW source material. Downstream users should account for domain and content bias.
• The published benchmark is small and should be treated as a sanity check rather than a full leaderboard result.
• Transcriptions may still contain hallucinations, punctuation differences, or style-specific handling of non-speech vocalizations.

License and Use

The base model Qwen/Qwen3-ASR-0.6B is released under Apache-2.0.

This fine-tuned checkpoint was trained on litagin/Galgame_Speech_ASR_16kHz. Users must review and comply with the dataset license and upstream terms before redistribution, commercial use, or further fine-tuning. This model card does not grant rights beyond the upstream model and dataset licenses.