Downloads · 30 days
97
1% of all-time downloads
faster-whisper-large-v2-japanese-5k-steps
zh-plus/faster-whisper-large-v2-japanese-5k-steps
faster-whisper-large-v2-japanese-5k-steps is a automatic speech recognition model from zh-plus. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
Converted from clu-ling/whisper-large-v2-japanese-5k-steps using CTranslate2.
All-time downloads
7.1K
Public
Repo size
3.1 GB
Likes
23
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- Jul 3, 2023
- Updated
- Jul 3, 2023
- SHA
- 4063039c
Model card
From the Hugging Face model README
Converted from clu-ling/whisper-large-v2-japanese-5k-steps using CTranslate2.
Usage:
-
Install
pip install faster-whisper(Check faster-whisper for detailed instructions.) -
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))
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Languages
- ja
- Created
- Jul 3, 2023
- Updated
- Jul 3, 2023