Mirrors/VoiceCraft
1
0
Fork 0
mirror of https://github.com/jasonppy/VoiceCraft.git synced 2025-12-23 07:09:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

change default inference from top-p to top-k sampling, massive performance gain

Browse Source
This commit is contained in:
pyp_l40
2025-03-15 18:16:27 -05:00
parent 013a21c70d
commit 7121981bb4
6 changed files with 12 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
gradio_app.py
View File

@@ -512,9 +512,9 @@ def get_app():
info="set to 0 to use less VRAM, but with slower inference")
left_margin = gr.Number(label="left_margin", value=0.08, info="margin to the left of the editing segment")
right_margin = gr.Number(label="right_margin", value=0.08, info="margin to the right of the editing segment")
top_p = gr.Number(label="top_p", value=0.9, info="0.9 is a good value, 0.8 is also good")
top_p = gr.Number(label="top_p", value=1, info="do not do topp sampling therefore set it to 1")
temperature = gr.Number(label="temperature", value=1, info="haven't try other values, do not recommend to change")
top_k = gr.Number(label="top_k", value=0, info="0 means we don't use topk sampling, because we use topp sampling")
top_k = gr.Number(label="top_k", value=40, info="40 is a good default, can also try 20, 30")
codec_audio_sr = gr.Number(label="codec_audio_sr", value=16000, info='encodec specific, Do not change')
codec_sr = gr.Number(label="codec_sr", value=50, info='encodec specific, Do not change')
silence_tokens = gr.Textbox(label="silence tokens", value="[1388,1898,131]", info="encodec specific, do not change")