modelscope/ClearerVoice-Studio
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
Supports speech super-resolution (bandwidth extension to 48kHz), audio-visual speaker extraction conditioned on face/gesture/EEG signals, and multi-format audio input (wav, mp3, flac, opus, etc.). The toolkit provides unified inference via a NumPy-array interface for flexible pipeline integration, plus separate training modules with data generation scripts for enhancement, separation, and super-resolution tasks. Integrates with ModelScope and HuggingFace for model distribution and includes SpeechScore, a quality assessment toolkit with intrusive and non-intrusive metrics (PESQ, STOI, DNSMOS, NISQA, DISTILL_MOS).
3,962 stars. No commits in the last 6 months.
Stars
3,962
Forks
325
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/modelscope/ClearerVoice-Studio"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
espnet/espnet
End-to-End Speech Processing Toolkit
yeyupiaoling/PPASR
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
flashlight/wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
yeyupiaoling/PaddlePaddle-DeepSpeech
基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。
philipperemy/deep-speaker
Deep Speaker: an End-to-End Neural Speaker Embedding System.