vosk 0.3.45

Offline open source speech recognition API based on Kaldi and Vosk

Stars: 6959, Watchers: 6959, Forks: 987, Open Issues: 448

The alphacep/vosk-api repo was created 4 years ago and the last code push was 23 hours ago.
The project is extremely popular with a mindblowing 6959 github stars!

How to Install vosk

You can install vosk using pip

pip install vosk

or add it to a project with poetry

poetry add vosk

Package Details

Author

Alpha Cephei Inc

License

Homepage

https://github.com/alphacep/vosk-api

PyPi:

https://pypi.org/project/vosk/

GitHub Repo:

https://github.com/alphacep/vosk-api

Classifiers

• Software Development/Libraries/Python Modules

Related Packages

Errors

A list of common vosk errors.

Code Examples

Here are some vosk code examples and snippets.

GitHub Issues

The vosk package has 448 open issues on GitHub

• Clearing input buffer before capturing new data
• Progress status or progress bar
• is vosk model free for lifetime?
• Method for training model with multiple languages
• Fine-tune the model released by vosk
• Guidance on registering and deploying model in cloud environment
• Is there a demo version for C++?
• Sentence timestamp in a large text file
• Add Phoneme labels and timestamps - take two
• Loading CARPA model from ../vosk-model-en-in-0.5/rescore/G.carpa Segmentation fault
• feat: enable usage of remote server and not only localhost
• Failed graph compilation
• Python binding: strange effect when reusing KaldiRecognizer (Reset not working properly?)
• How to increase the accuracy of the vosk module in Python?
• 0% Precision when using French Model

See more issues on GitHub