Paraformer (FunASR)

Non-autoregressive ASR model by Alibaba achieving fast parallel transcription.

Open SourceSelf HostedOffline CapableGPU Required (4GB+ VRAM)
0.0 (0)

About

Paraformer by Alibaba DAMO Academy (part of FunASR) is a non-autoregressive ASR model that transcribes in parallel rather than sequentially. Achieves competitive accuracy with much faster inference. Supports Chinese and English. MIT license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
MIT
Minimum VRAM
4 GB
Added
Apr 3, 2026

Similar Tools

Featured

General-purpose speech recognition model by OpenAI trained on 680K hours of multilingual audio.

Open SourceSelf HostedOffline
Easy
0.0 (0)
Featured

High-performance C/C++ port of Whisper for CPU-based speech recognition.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Offline speech recognition toolkit supporting 20+ languages with small models.

Open SourceSelf HostedOffline
Easy
0.0 (0)