From 2e0e5d83303e55b10402a3c95200a456a49a4b09 Mon Sep 17 00:00:00 2001 From: lipku Date: Tue, 1 Apr 2025 19:19:25 +0800 Subject: [PATCH] fix spelling mistakes --- README.md | 2 +- README_ZH.md | 2 +- basereal.py | 4 ++-- ttsreal.py | 26 +++++++++++++------------- 4 files changed, 17 insertions(+), 17 deletions(-) diff --git a/README.md b/README.md index e6e8eec..3fd2e04 100644 --- a/README.md +++ b/README.md @@ -44,7 +44,7 @@ For setting up the linux cuda environment, you can refer to this article https:/ ## 2. Quick Start - Download the models -Baidu Cloud Disk Password: ltua +Quark Cloud Disk Google Drive Copy wav2lip256.pth to the models folder of this project and rename it to wav2lip.pth; Extract wav2lip256_avatar1.tar.gz and copy the entire folder to the data/avatars folder of this project. diff --git a/README_ZH.md b/README_ZH.md index 1e427cc..f6f3330 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -45,7 +45,7 @@ linux cuda环境搭建可以参考这篇文章 https://zhuanlan.zhihu.com/p/6749 ## 2. Quick Start - 下载模型 -百度云盘 密码: ltua +夸克云盘 GoogleDriver 将wav2lip256.pth拷到本项目的models下, 重命名为wav2lip.pth; 将wav2lip256_avatar1.tar.gz解压后整个文件夹拷到本项目的data/avatars下 diff --git a/basereal.py b/basereal.py index edb722c..8f408c0 100644 --- a/basereal.py +++ b/basereal.py @@ -35,7 +35,7 @@ import soundfile as sf import av from fractions import Fraction -from ttsreal import EdgeTTS,VoitsTTS,XTTS,CosyVoiceTTS,FishTTS,TencentTTS +from ttsreal import EdgeTTS,SovitsTTS,XTTS,CosyVoiceTTS,FishTTS,TencentTTS from logger import logger from tqdm import tqdm @@ -57,7 +57,7 @@ class BaseReal: if opt.tts == "edgetts": self.tts = EdgeTTS(opt,self) elif opt.tts == "gpt-sovits": - self.tts = VoitsTTS(opt,self) + self.tts = SovitsTTS(opt,self) elif opt.tts == "xtts": self.tts = XTTS(opt,self) elif opt.tts == "cosyvoice": diff --git a/ttsreal.py b/ttsreal.py index fa98a7b..ed0cdf7 100644 --- a/ttsreal.py +++ b/ttsreal.py @@ -107,9 +107,9 @@ class EdgeTTS(BaseTTS): eventpoint=None streamlen -= self.chunk if idx==0: - eventpoint={'status':'start','text':text,'msgenvent':textevent} + eventpoint={'status':'start','text':text,'msgevent':textevent} elif streamlen0: #skip last frame(not 20ms) @@ -219,16 +219,16 @@ class FishTTS(BaseTTS): while streamlen >= self.chunk: eventpoint=None if first: - eventpoint={'status':'start','text':text,'msgenvent':textevent} + eventpoint={'status':'start','text':text,'msgevent':textevent} first = False self.parent.put_audio_frame(stream[idx:idx+self.chunk],eventpoint) streamlen -= self.chunk idx += self.chunk - eventpoint={'status':'end','text':text,'msgenvent':textevent} + eventpoint={'status':'end','text':text,'msgevent':textevent} self.parent.put_audio_frame(np.zeros(self.chunk,np.float32),eventpoint) ########################################################################################### -class VoitsTTS(BaseTTS): +class SovitsTTS(BaseTTS): def txt_to_audio(self,msg): text,textevent = msg self.stream_tts( @@ -316,12 +316,12 @@ class VoitsTTS(BaseTTS): while streamlen >= self.chunk: eventpoint=None if first: - eventpoint={'status':'start','text':text,'msgenvent':textevent} + eventpoint={'status':'start','text':text,'msgevent':textevent} first = False self.parent.put_audio_frame(stream[idx:idx+self.chunk],eventpoint) streamlen -= self.chunk idx += self.chunk - eventpoint={'status':'end','text':text,'msgenvent':textevent} + eventpoint={'status':'end','text':text,'msgevent':textevent} self.parent.put_audio_frame(np.zeros(self.chunk,np.float32),eventpoint) ########################################################################################### @@ -382,12 +382,12 @@ class CosyVoiceTTS(BaseTTS): while streamlen >= self.chunk: eventpoint=None if first: - eventpoint={'status':'start','text':text,'msgenvent':textevent} + eventpoint={'status':'start','text':text,'msgevent':textevent} first = False self.parent.put_audio_frame(stream[idx:idx+self.chunk],eventpoint) streamlen -= self.chunk idx += self.chunk - eventpoint={'status':'end','text':text,'msgenvent':textevent} + eventpoint={'status':'end','text':text,'msgevent':textevent} self.parent.put_audio_frame(np.zeros(self.chunk,np.float32),eventpoint) ########################################################################################### @@ -505,13 +505,13 @@ class TencentTTS(BaseTTS): while streamlen >= self.chunk: eventpoint=None if first: - eventpoint={'status':'start','text':text,'msgenvent':textevent} + eventpoint={'status':'start','text':text,'msgevent':textevent} first = False self.parent.put_audio_frame(stream[idx:idx+self.chunk],eventpoint) streamlen -= self.chunk idx += self.chunk last_stream = stream[idx:] #get the remain stream - eventpoint={'status':'end','text':text,'msgenvent':textevent} + eventpoint={'status':'end','text':text,'msgevent':textevent} self.parent.put_audio_frame(np.zeros(self.chunk,np.float32),eventpoint) ########################################################################################### @@ -583,10 +583,10 @@ class XTTS(BaseTTS): while streamlen >= self.chunk: eventpoint=None if first: - eventpoint={'status':'start','text':text,'msgenvent':textevent} + eventpoint={'status':'start','text':text,'msgevent':textevent} first = False self.parent.put_audio_frame(stream[idx:idx+self.chunk],eventpoint) streamlen -= self.chunk idx += self.chunk - eventpoint={'status':'end','text':text,'msgenvent':textevent} + eventpoint={'status':'end','text':text,'msgevent':textevent} self.parent.put_audio_frame(np.zeros(self.chunk,np.float32),eventpoint) \ No newline at end of file