Seamless Communication Demo
- Direct Speech-to-Speech Translation With Discrete Units: [demo, paper, code]
- Textless Speech-to-Speech Translation on Real Data: [demo, paper, code]
- Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data
Augmentation: [demo, paper, code]
- A Holistic Cascade System, Benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation
[demo]
- Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation: [demo]