README.md

---
language:
- ja
tags:
- audio
- automatic-speech-recognition
- whisper
- ctranslate2
- faster-whisper
base_model: efwkjn/whisper-ja-1.5B
pipeline_tag: automatic-speech-recognition
library_name: ctranslate2
---

# whisper-ja-1.5B-ct2

CTranslate2 conversion of [efwkjn/whisper-ja-1.5B](https://huggingface.co/efwkjn/whisper-ja-1.5B) with **bfloat16** weights, for use with [faster-whisper](https://github.com/SYSTRAN/faster-whisper).

The original model is a Whisper large-v3 finetune for Japanese ASR, achieving competitive/SOTA CER across tested sets. See the original repo for details and [benchmarks](https://huggingface.co/efwkjn/whisper-ja-1.5B/blob/main/BENCH.md).

## Usage

```python
from faster_whisper import WhisperModel

model = WhisperModel("TransWithAI/whisper-ja-1.5B-ct2", device="cuda", compute_type="bfloat16")

segments, info = model.transcribe("audio.wav", language="ja")
for segment in segments:
    print(f"[{segment.start:.2f} -> {segment.end:.2f}] {segment.text}")
```

## Conversion

Converted with CTranslate2 4.7.2:

```bash
ct2-transformers-converter \
    --model efwkjn/whisper-ja-1.5B \
    --output_dir whisper-ja-1.5B-ct2 \
    --quantization bfloat16 \
    --copy_files tokenizer.json preprocessor_config.json
```

## Acknowledgements

All credit for the model goes to [efwkjn](https://huggingface.co/efwkjn). Acknowledgements from the original model card:

* Train sets: OOPPEENN, Reazon, 小虫哥_, Common Voice 20, deepghs
* Test sets: KitsuneX07, TEDxJP, kotoba-tech, Saruwatari-lab, grider-withourai