SPEECH · EMOTION · AUDIO EVENTS
SenseVoice
@QWENAUDIO
Let your partner hear language, emotions, and environmental sounds beyond words.
SenseVoice puts transcription, language, emotion and audio events into the same auditory model, allowing partners to obtain richer sound context than pure text.
Project address (can be copied to AI):https://github.com/QwenAudio/SenseVoice
PROJECT INTRO
Project introduction
SenseVoiceSmall jointly provides speech recognition, language recognition, emotion recognition and audio event detection for Chinese, Cantonese, English, Japanese and Korean.
It is suitable for converting calls or voice messages into a context that contains text, emotion and environmental tags, and then leaves it to the partner to determine how to respond.
- Suitable for:People who want to make AI understand speech content, emotions, and sound events simultaneously.
- Platform:Python is self-hosted and can be connected to inference environments such as FunASR.
- Usage:Download the model weights, follow the README to run inference or connect to an existing voice service.
- License:Source code and models are used according to the repository LICENSE and model terms.
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...