mirror of
https://github.com/RVC-Boss/GPT-SoVITS.git
synced 2025-04-06 03:57:44 +08:00
66 lines
2.7 KiB
Python
66 lines
2.7 KiB
Python
# -*- coding:utf-8 -*-
|
|
|
|
import argparse
|
|
import os
|
|
import traceback
|
|
from tqdm import tqdm
|
|
|
|
from funasr import AutoModel
|
|
|
|
path_asr = 'tools/asr/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch'
|
|
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_asr = path_asr if os.path.exists(path_asr) else "iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-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"
|
|
|
|
model = AutoModel(
|
|
model = path_asr,
|
|
model_revision = "v2.0.4",
|
|
vad_model = path_vad,
|
|
vad_model_revision = "v2.0.4",
|
|
punc_model = path_punc,
|
|
punc_model_revision = "v2.0.4",
|
|
)
|
|
|
|
def execute_asr(input_folder, output_folder, model_size, language):
|
|
input_file_names = os.listdir(input_folder)
|
|
input_file_names.sort()
|
|
|
|
output = []
|
|
output_file_name = os.path.basename(input_folder)
|
|
|
|
for name in tqdm(input_file_names):
|
|
try:
|
|
text = model.generate(input="%s/%s"%(input_folder, name))[0]["text"]
|
|
output.append(f"{input_folder}/{name}|{output_file_name}|{language.upper()}|{text}")
|
|
except:
|
|
return print(traceback.format_exc())
|
|
|
|
output_folder = output_folder or "output/asr_opt"
|
|
os.makedirs(output_folder, exist_ok=True)
|
|
output_file_path = os.path.abspath(f'{output_folder}/{output_file_name}.list')
|
|
|
|
with open(output_file_path, "w", encoding="utf-8") as f:
|
|
f.write("\n".join(output))
|
|
print(f"ASR 任务完成->标注文件路径: {output_file_path}\n")
|
|
return output_file_path
|
|
|
|
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'],
|
|
help="Language of the audio files.")
|
|
|
|
cmd = parser.parse_args()
|
|
execute_asr(
|
|
input_folder = cmd.input_folder,
|
|
output_folder = cmd.output_folder,
|
|
model_size = cmd.model_size,
|
|
language = cmd.language,
|
|
) |