xingchensong/S3Tokenizer
Reverse engineering of supervised semantic speech tokenizer
View on index · View in 3D Map
Related repos
- speech-to-speech pipeline using open models for voice detection, transcription, language modeling, and speech synthesis
- PyTorch toolkit for conversational AI
- human-level text-to-speech using style diffusion and large speech models
- extracts voice features for speaker recognition and fake speech detection
- Synthesizes speech without tokenizers
- AI text-to-speech tool with fast voice cloning and emotion
- Single-stage text-to-speech model with adversarial learning
- Text-to-speech engine for long-form audio
- text-to-speech library for generating voices with controllable style and speaker traits
- AI multilingual speech recognition, translation, dubbing web app
