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 the FunASR toolkit, is a non-autoregressive speech recognition model that decodes a whole utterance in parallel rather than token by token, giving fast inference at competitive accuracy. FunASR adds VAD segmentation, punctuation, speaker diarization, and timestamps through a single API across many languages. Released under the 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

Related Tools

Whisper extension providing word-level timestamps for transcription.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Multilingual ASR model by NVIDIA supporting 4 languages with translation.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Convolution-augmented transformer for speech recognition in ESPnet toolkit.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)

Pre-trained speech models for STT, TTS, and VAD with simple PyTorch integration.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

CLI tool that transcribes audio 10x faster using pipeline optimizations.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Open-source speaker diarization and voice activity detection toolkit.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Browse all Speech-to-Text / Speech Recognition tools