Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
- asr
- speech-recognition
- speech-to-text
- cross-lingual
132,241 visible repositories in the index
1–14 of 14 · Most stars
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
TranslatedA tool focused on AI multimodal translation that automatically translates, with one click, RPG/SLG games, Epub/TXT novels, PDF/Word/MD documents, Srt/Ass/Vtt subtitles, as well as manga images, audio, video, and more.
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
WhisperPlus: Faster, Smarter, and More Capable 🚀
A complete video subtitle editing React component with AI-powered speech recognition and visual editing capabilities.
Whisper based Japanese subtitle generator
WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.
Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the same time, this project also supports MelSpectrogram, Spectrogram data preprocessing methods
First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. ⭐**
Evidence-aware Japanese speech visualization: pitch and intonation, waveform inspection, and experimental alignment.