Japanese Proper-Noun Fine-tuned Qwen3-ASR
A fine-tuned checkpoint of Qwen/Qwen3-ASR-1.7B optimized for Japanese automatic speech recognition.
This variant is specifically trained to improve recognition of Japanese proper nouns, organization names, product names, service names, and kanji-heavy expressions that general-purpose ASR models tend to mistranscribe.
Intended Use
Designed for Japanese ASR tasks requiring accurate transcription of:
- Proper nouns (people, places, organizations)
- Difficult or uncommon kanji spellings
- Company and product names
- Mixed Japanese/English technical terminology
Example Normalizations
Product / Company Names
| Spoken | Expected output |
|---|---|
| ジェミニ | Gemini |
| アンスロピック | Anthropic |
| ノートブックLM | NotebookLM |
Japanese Numerals
| Spoken | Expected output |
|---|---|
| 一万二千三百四十五 | 1万2345 |
| 十人 | 10人 |
Math / Code
| Spoken | Expected output |
|---|---|
| AイコールAプラス1 | A=A+1 |
Model Details
| Base model | Qwen/Qwen3-ASR-1.7B |
| Task | Automatic speech recognition |
| Language | Japanese (ja), English (en) |
| Fine-tuning focus | Japanese proper nouns & technical vocabulary |
Quickstart
Install the runtime package:
pip install -U qwen-asr
Transcribe a local audio file:
import torch
from qwen_asr import Qwen3ASRModel
model = Qwen3ASRModel.from_pretrained(
"neosophie/Qwen3-ASR-1.7B-JA",
dtype=torch.bfloat16,
device_map="cuda:0",
)
results = model.transcribe(audio="/path/to/audio.wav")
print(results[0].language)
print(results[0].text)
Acknowledgments
- Qwen3-ASR-1.7B — base model by Alibaba Cloud
Built by Neosophie