ZK-AI
/
livetalking
mirror of https://gitee.com/dumengxue/livetalking.git
3
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add demo video

This commit is contained in:
lihengzhong 2024-01-10 15:06:08 +08:00
parent 46b0f5abab
commit d1f5697169
3 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -1,6 +1,9 @@
A streaming digital human based on the Ernerf model， realize audio video synchronous dialogue. It can basically achieve commercial effects. A streaming digital human based on the Ernerf model， realize audio video synchronous dialogue. It can basically achieve commercial effects.
基于ernerf模型的流式数字人，实现音视频同步对话。基本可以达到商用效果 基于ernerf模型的流式数字人，实现音视频同步对话。基本可以达到商用效果
<video id="video" controls="" preload="none" poster="封面">
<source id="mp4" src="assets/demo.mp4" type="video/mp4">
</video>
## Installation ## Installation

BIN
assets/demo.mp4 Normal file
View File

Binary file not shown.

8
nerfreal.py
View File

@ -64,7 +64,7 @@ class NeRFReal:
sc.stream_height = self.H sc.stream_height = self.H
sc.stream_fps = fps sc.stream_fps = fps
sc.stream_bitrate = 1000000 sc.stream_bitrate = 1000000
sc.stream_profile = 'main' #'high444' # 'main' sc.stream_profile = 'baseline' #'high444' # 'main'
sc.audio_channel = 1 sc.audio_channel = 1
sc.sample_rate = 16000 sc.sample_rate = 16000
sc.stream_server = opt.push_url sc.stream_server = opt.push_url
@ -178,7 +178,7 @@ class NeRFReal:
for _ in range(2): for _ in range(2):
self.asr.run_step() self.asr.run_step()
self.test_step() self.test_step()
delay = 0.04 - (time.time() - t) #40ms # delay = 0.04 - (time.time() - t) #40ms
if delay > 0: # if delay > 0:
time.sleep(delay) # time.sleep(delay)