Skip to content

Conversation

@thewh1teagle
Copy link
Contributor

Added usage examples with sample audio recorded by me :P
Also added pyproject section so tools like uv will run without error as they expect that in the pyproject file

Continue from

import stable_whisper

model = stable_whisper.load_faster_whisper('ivrit-ai/whisper-large-v3-turbo-ct2')
segs = model.transcribe('audio.wav', language='he') # Use word_timestamps=True for word-level timestamps
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

stable_ts turn on word level timestamps - so this comment is misleading.
You can just replace it with "Stable Whisper enables word level timestamps by default"

@thewh1teagle
Copy link
Contributor Author

PR ready. the only question I still have is if the examples uses the latest model currently since I noticed that you released new model recently

@yoadsn yoadsn merged commit 25df8bf into ivrit-ai:master Apr 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants