前言

傳言GPT-SoVITS作為當前與BertVits2.3并列的TTS大模型，于是本地搭了一個，簡單說一下坑。

搭建

下載

到GitHub點擊此處下載
https://github.com/RVC-Boss/GPT-SoVITS

解壓

解壓到全英文目錄

VSCode打開

使用VSCode打開，切到conda并clone一個之前BertVits的環(huán)境（沒環(huán)境的自己先做一個Python3.10的配好PyTorch的）

安裝依賴包

使用下面語句安裝依賴

pip install -r requirements.txt

修改內(nèi)容

根據(jù)issues內(nèi)大家討論的結(jié)果，這樣操作是實測可行的，但是之后作者應(yīng)該會優(yōu)化，截止發(fā)文這么改是沒問題的，以后可能不用改了
https://github.com/RVC-Boss/GPT-SoVITS/issues/26

1.重新安裝版本

輸入下面的指令重新安裝一下對應(yīng)版本的

pip install funasr==0.8.7
pip install modelscope==1.10.0

2.修改文件內(nèi)容

將 tools\damo_asr\cmd-asr.py 文件中的

inference_pipeline = pipeline(task=Tasks.auto_speech_recognition,model='tools/damo_asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',vad_model='tools/damo_asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch',punc_model='tools/damo_asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
)

改成

inference_pipeline = pipeline(task=Tasks.auto_speech_recognition,model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
)

根據(jù)我的研究，原因是 git clone 的那幾個模型的配置文件和它自動下載的內(nèi)容不一樣

修改后源碼如下

# -*- coding:utf-8 -*-from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
import sys,os,traceback
dir=sys.argv[1]
# opt_name=dir.split("\\")[-1].split("/")[-1]
opt_name=os.path.basename(dir)path_asr='tools/damo_asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch'
path_vad='tools/damo_asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch'
path_punc='tools/damo_asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch'
path_asr=path_asr if os.path.exists(path_asr)else "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
path_vad=path_vad if os.path.exists(path_vad)else "damo/speech_fsmn_vad_zh-cn-16k-common-pytorch"
path_punc=path_punc if os.path.exists(path_punc)else "damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
# inference_pipeline = pipeline(
#     task=Tasks.auto_speech_recognition,
#     model=path_asr,
#     vad_model=path_vad,
#     punc_model=path_punc,
# )
inference_pipeline = pipeline(task=Tasks.auto_speech_recognition,model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch',punc_model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch',
)opt=[]
for name in os.listdir(dir):try:text = inference_pipeline(audio_in="%s/%s"%(dir,name))["text"]opt.append("%s/%s|%s|ZH|%s"%(dir,name,opt_name,text))except:print(traceback.format_exc())opt_dir="output/asr_opt"
os.makedirs(opt_dir,exist_ok=True)
with open("%s/%s.list"%(opt_dir,opt_name),"w",encoding="utf-8")as f:f.write("\n".join(opt))

運行

在環(huán)境中輸入，即可正常啟動

python webui.py

總結(jié)

能夠有感情的朗讀了，不錯