FunASR is an end-to-end speech recognition toolkit. It provides tools for building, training and deploying speech-processing systems for offline, streaming and edge use.
The project brings together automatic speech recognition, voice activity detection, punctuation restoration, speaker diarization, emotion recognition and audio-event detection within a common framework. It supports a range of model families, including Fun-ASR-Nano, SenseVoice, Paraformer and integrations for other speech models, with deployment options spanning local CPU or GPU inference, WebSocket streaming and API-based serving.
This is free and open source software.
Key Features
- Automatic speech recognition for offline files, batch workloads and low-latency streaming applications.
- Multilingual model support, with language coverage depending on the selected checkpoint.
- Voice activity detection for locating speech segments and removing non-speech regions before transcription.
- Punctuation models for turning raw recognition output into more readable transcriptions.
- Speaker diarization pipelines that combine speech segmentation with speaker identification models.
- Emotion recognition and audio-event detection through models such as SenseVoice and emotion2vec.
- Timestamp generation for applications that need time-aligned transcripts or subtitle production.
- Hotword support for improving recognition of selected names, terminology and other important vocabulary.
- Streaming recognition with models such as Paraformer and WebSocket-based real-time serving.
- Model training and fine-tuning facilities for adapting speech recognition systems to particular datasets or domains.
- CPU and GPU inference, with CUDA acceleration available for suitable PyTorch installations.
- vLLM integration for accelerating compatible models and processing larger inference workloads.
- OpenAI-compatible API server for integrating transcription into applications that already use familiar API conventions.
- Command-line tools for transcription, training, model export and server operation.
- Model zoo covering speech recognition, punctuation, voice activity detection, speaker processing and related audio tasks.
Website: github.com/modelscope/FunASR
Support:
Developer: Speech Lab of Alibaba Group
License: MIT License
FunASR is written in Python and C. Learn Python with our recommended free books and free tutorials. Learn C with our recommended free books and free tutorials.
Related Software
| Speech Recognition Tools | |
|---|---|
| Whisper | Automatic speech recognition (system trained on 680,000 hours of data |
| Flashlight | Fast, flexible machine learning library written entirely in C++. |
| Coqui STT | Deep-learning toolkit for training and deploying speech-to-text models |
| Kaldi | C++ toolkit designed for speech recognition researchers. |
| SpeechBrain | All-in-one conversational AI toolkit based on PyTorch |
| Handy | Offline speech-to-text application |
| ESPnet | End-to-End speech processing toolkit |
| deepspeech.pytorch | Implementation of DeepSpeech2 using Baidu Warp-CTC. |
| Whispering | Transcription application with global speech-to-text functionality |
| Julius | Two-pass large vocabulary continuous speech recognition engine |
| CMUSphinx | Speech recognition system for mobile and server applications |
| Simon | Flexible speech recognition software |
| hyprwhspr | Native speech-to-text designed for Arch / Omarchy |
| ostt | Open Speech-to-Text |
| DeepSpeech | TensorFlow implementation of Baidu's DeepSpeech architecture. |
| OpenSeq2Seq | TensorFlow-based toolkit for sequence-to-sequence models |
| Eesen | End-to-End Speech Recognition |
Read our verdict in the software roundup.
 Explore our comprehensive directory of recommended free and open source software. Our carefully curated collection spans every major software category.This directory is part of our ongoing series of informative articles for Linux enthusiasts. It features hundreds of detailed reviews, along with open source alternatives to proprietary solutions from major corporations such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk. You’ll also find interesting projects to try, hardware coverage, free programming books and tutorials, and much more. Discovered a useful open source Linux program that we haven’t covered yet? Let us know by completing this form. |
Please read our Comment Policy before commenting.