blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-10-07 15:19:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

多进程优化转写效率，提高效率

Browse Source 
多进程优化转写效率，提高效率
This commit is contained in:
刘悦 2024-01-26 14:13:22 +08:00 committed by GitHub
parent 813cf96e50
commit 2bbc37e5e8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 43 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
tools/damo_asr/cmd-asr.py
View File

@ -2,33 +2,60 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.models import Model
import multiprocessing
import sys,os,traceback
from threading import Lock
lock = Lock()
# 进程数
processes = 2
dir=sys.argv[1]
# opt_name=dir.split("\\")[-1].split("/")[-1]
opt_name=os.path.basename(dir)
# FunAsr三语转写model
lang2model = {
'zh': 'tools/damo_asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
'ja': "tools/damo_asr/models/speech_UniASR_asr_2pass-ja-16k-common-vocab93-tensorflow1-offline",
"en": "tools/damo_asr/models/speech_UniASR_asr_2pass-en-16k-common-vocab1080-tensorflow1-offline",
}
model = Model.from_pretrained(lang2model["zh"])
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,
model=model,
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',
)
opt=[]
for name in os.listdir(dir):
def process_audio_file(dir,filename,name,opt_name):
try:
text = inference_pipeline(audio_in="%s/%s" % (dir, name))["text"]
opt.append("%s/%s|%s|ZH|%s"%(dir,name,opt_name,text))
with lock:
with open(filename,"a",encoding="utf-8")as f:f.write("%s/%s|%s|ZH|%s\n" % (dir, name, opt_name, text.strip()))
except:
print(traceback.format_exc())
def run__process(): # 主进程
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))
filename = "%s/%s.list"%(opt_dir,opt_name)
if os.path.exists(filename):
os.remove(filename)
with multiprocessing.Pool(processes=processes) as pool:
pool.starmap(process_audio_file, [(dir,filename,name ,opt_name) for name in os.listdir(dir)])
if __name__ == '__main__':
run__process()