---
license: mit
datasets:
- mozilla-foundation/common_voice_11_0
language:
- ja
pipeline_tag: automatic-speech-recognition
tags:
- pytorch
- faster-whisper
- whisper
- CTranslate2
metrics:
- wer
---

Converted from [clu-ling/whisper-large-v2-japanese-5k-steps](https://huggingface.co/clu-ling/whisper-large-v2-japanese-5k-steps) using [CTranslate2](https://github.com/OpenNMT/CTranslate2).

Usage:
1. Install `pip install faster-whisper` (Check [faster-whisper](https://github.com/guillaumekln/faster-whisper) for detailed instructions.)

2. ```python
   from faster_whisper import WhisperModel

   model = WhisperModel('zh-plus/faster-whisper-large-v2-japanese-5k-steps', device="cuda", compute_type="float16")
   segments, info = model.transcribe("audio.mp3", beam_size=5)

   print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

   for segment in segments:
       print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
   ```