HumeAI/tada
Unified speech-language model with 1:1 alignment
View on index · View in 3D Map
Related repos
- open-weight text-to-speech model for fast, natural voice synthesis
- Text-to-speech library with advanced models in 17 languages (legacy models in 1100+), and tools for custom voice training
- Training and inference for multimodal language models
- large language model tutorials and training basics from scratch
- bilingual AI turns text into expressive dialogue speech
- Text-to-dialogue model, clones voices
- Translates speech across languages with voice transfer
- Speech recognition and forced alignment for 52 languages
- Runs large language models locally
- toolkit for finetuning large language models like Llama and Mistral on your own machine
