4096维的speech_token具体是哪些？能否提供token样例？

FunAudioLLM / CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

https://funaudiollm.github.io/

Apache License 2.0

4.87k stars 494 forks source link

Open rainskyfyy opened 4 hours ago

rainskyfyy commented 4 hours ago

cosyvoice.yaml文件中第22行设置了“speech_token_size: 4096”，请问这4096个token具体是哪些？方便提供token的示例吗？

aluminumbox commented 2 hours ago

from index 0 to 4095