FunASR

What it is

FunASR is a comprehensive end-to-end speech recognition toolkit that includes state-of-the-art pretrained models and supports multiple audio processing tasks such as voice activity detection and text post-processing. It's designed to help developers build robust speech recognition applications efficiently.

FunASR stands out as a comprehensive toolkit offering state-of-the-art pretrained models and flexibility for various speech recognition tasks, making it ideal for developers looking to quickly build robust applications.

When it fits — and when it doesn’t

Known weaknesses

Each one links to the public issue, changelog or docs page it came from, where we have one.

1. 01

   Limited documentation and examples for advanced use cases

   Community forum and issue tracker show frequent requests for detailed guides on customization

2. 02

   Performance issues with large datasets

   Benchmarks indicate significant slowdowns when processing audio files over 1 hour in length

What it does well

• State-of-the-art pretrained models for speech recognition and related tasks.

• Supports voice activity detection and text post-processing.

• Flexible configuration options for customizing model performance.

Pricing

Free tier

YesOpen source — free to use

Paid from

$0

Model

Flat rate

Enterprise plan

No

Pricing not independently confirmed — check the vendor’s page.