CanCLID/zoengjyutgaai
Viewer • Updated • 117k • 6.01k • 30
本模型係 GPT-SoVITS v2ProPlus 用咗全部張悦楷講古語音數據集 CanCLID/zoengjyutgaai,即總共 188.67 個鐘數據微調出嚟嘅。語音合成效果請見laubonghaudoi/zoengjyutgaai_tts。
模型用嘅係 v2ProPlus 版,詳情請見 GPT‐SoVITS‐features (各版本特性)
sovits/e1_e50_s5950.pthgpt/dpo1-e200.ckptgpt/dpo1-e600.ckptgpt/dpo1-e1000.ckptfrom huggingface_hub import hf_hub_download
# Download GPT model
gpt_model = hf_hub_download(
repo_id="laubonghaudoi/zoengjyutgaai_tts",
filename="gpt/dpo1-e1000.ckpt"
)
# Download SoVITS model
sovits_model = hf_hub_download(
repo_id="laubonghaudoi/zoengjyutgaai_tts",
filename="sovits/e1_e50_s5950.pth"
)
Base model
lj1995/GPT-SoVITS