mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 10:26:33 +00:00
Conversational Speech Model (CSM)
CSM is a speech generation model from Sesame, SesameAILabs/csm.
It can generate a conversational speech between two different speakers.
The speakers turn are delimited by the |
character in the prompt.
cargo run --example csm --features cuda -r -- \
--voices candle-examples/examples/csm/voices.safetensors \
--prompt "Hey how are you doing?|Pretty good, pretty good. How about you?"