{"library":"s3tokenizer","type":"library","category":null,"description":"S3Tokenizer is a Python library that provides a reverse-engineered PyTorch implementation of the Supervised Semantic Speech Tokenizer (S3Tokenizer), originally proposed in CosyVoice. It enables high-throughput batch inference and online speech code extraction. The current version is 0.3.0, and the library demonstrates a rapid release cadence, frequently adding support for newer CosyVoice versions and improving audio processing capabilities.","language":"python","status":"active","version":"0.3.0","tags":["audio","speech","tokenizer","pytorch","cosyvoice","nlp","ai","machine-learning"],"install":[{"cmd":"pip install s3tokenizer","imports":["import s3tokenizer\ntokenizer = s3tokenizer.load_model(\"speech_tokenizer_v1\")","import s3tokenizer\naudio = s3tokenizer.load_audio(\"path/to/audio.wav\")"]}],"homepage":null,"github":"https://github.com/xingchensong/S3Tokenizer","docs":null,"changelog":null,"pypi":"https://pypi.org/project/s3tokenizer/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":20,"avg_install_s":72.8,"avg_import_s":6.46,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/s3tokenizer/compatibility"},"provenance":{"verified_status":"timeout","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Sun Jul 05","install_tag":null}}