blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-04-05 19:41:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

https://github.com/RVC-Boss/GPT-SoVITS/issues/1419

Browse Source 
fix issue https://github.com/RVC-Boss/GPT-SoVITS/issues/1419
This commit is contained in:
RVC-Boss 2024-08-07 17:24:59 +08:00 committed by GitHub
parent 74edd5dcf9
commit bf289e030d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 40 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
tools/asr/funasr_asr.py
View File

@ -42,46 +42,47 @@ def execute_asr(input_folder, output_folder, model_size, language):
print(f"ASR 任务完成->标注文件路径: {output_file_path}\n")
return output_file_path
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input_folder", type=str, required=True,
help="Path to the folder containing WAV files.")
parser.add_argument("-o", "--output_folder", type=str, required=True,
help="Output folder to store transcriptions.")
parser.add_argument("-s", "--model_size", type=str, default='large',
help="Model Size of FunASR is Large")
parser.add_argument("-l", "--language", type=str, default='zh', choices=['zh','yue','auto'],
help="Language of the audio files.")
parser.add_argument("-p", "--precision", type=str, default='float16', choices=['float16','float32'],
help="fp16 or fp32")#还没接入
cmd = parser.parse_args()
path_vad = 'tools/asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch'
path_punc = 'tools/asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch'
path_vad = path_vad if os.path.exists(path_vad) else "iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
path_punc = path_punc if os.path.exists(path_punc) else "iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
vad_model_revision=punc_model_revision="v2.0.4"
if(cmd.language=="zh"):
path_asr = 'tools/asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch'
path_asr = path_asr if os.path.exists(path_asr) else "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model_revision="v2.0.4"
else:
path_asr = 'tools/asr/models/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online'
path_asr = path_asr if os.path.exists(path_asr) else "iic/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online"
model_revision="master"
path_vad=path_punc=vad_model_revision=punc_model_revision=None###友情提示：粤语带VAD识别可能会有少量shape不对报错的，但是不带VAD可以.不带vad只能分阶段单独加标点。不过标点模型对粤语效果真的不行…
model = AutoModel(
model=path_asr,
model_revision=model_revision,
vad_model=path_vad,
vad_model_revision=vad_model_revision,
punc_model=path_punc,
punc_model_revision=punc_model_revision,
)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input_folder", type=str, required=True,
help="Path to the folder containing WAV files.")
parser.add_argument("-o", "--output_folder", type=str, required=True,
help="Output folder to store transcriptions.")
parser.add_argument("-s", "--model_size", type=str, default='large',
help="Model Size of FunASR is Large")
parser.add_argument("-l", "--language", type=str, default='zh', choices=['zh','yue'],
help="Language of the audio files.")
parser.add_argument("-p", "--precision", type=str, default='float16', choices=['float16','float32'],
help="fp16 or fp32")#还没接入
cmd = parser.parse_args()
path_vad = 'tools/asr/models/speech_fsmn_vad_zh-cn-16k-common-pytorch'
path_punc = 'tools/asr/models/punc_ct-transformer_zh-cn-common-vocab272727-pytorch'
path_vad = path_vad if os.path.exists(path_vad) else "iic/speech_fsmn_vad_zh-cn-16k-common-pytorch"
path_punc = path_punc if os.path.exists(path_punc) else "iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch"
vad_model_revision=punc_model_revision="v2.0.4"
if(cmd.language=="zh"):
path_asr = 'tools/asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch'
path_asr = path_asr if os.path.exists(path_asr) else "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model_revision="v2.0.4"
else:
path_asr = 'tools/asr/models/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online'
path_asr = path_asr if os.path.exists(path_asr) else "iic/speech_UniASR_asr_2pass-cantonese-CHS-16k-common-vocab1468-tensorflow1-online"
model_revision="master"
path_vad=path_punc=vad_model_revision=punc_model_revision=None###友情提示：粤语带VAD识别可能会有少量shape不对报错的，但是不带VAD可以.不带vad只能分阶段单独加标点。不过标点模型对粤语效果真的不行…
model = AutoModel(
model=path_asr,
model_revision=model_revision,
vad_model=path_vad,
vad_model_revision=vad_model_revision,
punc_model=path_punc,
punc_model_revision=punc_model_revision,
)
execute_asr(
input_folder = cmd.input_folder,
output_folder = cmd.output_folder,