SenseVoice

Name: SenseVoice
Availability: OnlineOnly
Rating: 2.5 (8926 reviews)
Author: FunAudioLLM

FunAudioLLM/SenseVoice

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

★8.9kstars

MIT

Updated: 2w ago

GitHub

FunAudioLLM/SenseVoice

🧠

📋 Project at a Glance

Tap to expand

What's this?Models project leveraging asr and audio-analysis, built with C, open-source

Who made it?Maintained by FunAudioLLM team, 8.9K⭐ on GitHub, #169 out of 3201 in Models

Why does it exist?The FunAudioLLM team recognized that existing asr tools in Models were hard to use. SenseVoice was designed to make audio-analysis more accessible.

What can it do?Key use cases: audio-event-detection, cantonese, cross-lingual

How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/FunAudioLLM/SenseVoice | 官网 https://huggingface.co/spaces/FunAudioLLM/SenseVoice

Topics

asraudio-analysisaudio-event-detectioncantonesecross-lingualemotion-detectionfunasrlanguage-identificationllama-cppmultilingualmultilingual-asrpytorchsensevoicespeech-emotion-recognitionspeech-recognitionspeech-to-textspeech-understandingtranscriptionvoice-aiwhisper-alternative

More Models projects ← Back to All Rankings

🔗 More model projects

SenseVoice

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, an

★ 9.0kC

Fun-ASR

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multili

★ 1.5kC

Fun-ASR

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multili

★ 1.4kC

FunASR

Open-source speech recognition toolkit for training, inference, streaming ASR, V

★ 19.7kPython

SenseVoice

FunAudioLLM/SenseVoice

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

★8.9kstars

MIT

Updated: 2w ago

GitHub

FunAudioLLM/SenseVoice

🧠

📋 Project at a Glance

Tap to expand

What's this?Models project leveraging asr and audio-analysis, built with C, open-source

Who made it?Maintained by FunAudioLLM team, 8.9K⭐ on GitHub, #169 out of 3201 in Models

Why does it exist?The FunAudioLLM team recognized that existing asr tools in Models were hard to use. SenseVoice was designed to make audio-analysis more accessible.

What can it do?Key use cases: audio-event-detection, cantonese, cross-lingual

Topics

More Models projects ← Back to All Rankings

🔗 More model projects

SenseVoice

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, an

★ 9.0kC

Fun-ASR

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multili

★ 1.5kC

Fun-ASR

Open-source LLM-based ASR model family for Chinese, dialect, accent, and multili

★ 1.4kC

FunASR

Open-source speech recognition toolkit for training, inference, streaming ASR, V

★ 19.7kPython