mirror of
https://github.com/RVC-Boss/GPT-SoVITS.git
synced 2025-04-06 03:57:44 +08:00
29f22115fb
* Update README * Optimize-English-G2P * docs: change akward expression * docs: update Changelog_KO.md * Fix CN punc in EN,add 's match * Adjust normalize and g2p logic * Update zh_CN.json * Update README (#827) Update README.md Update some outdated file paths and commands * 修复英文多音字,调整字典热加载,新增姓名匹配 (#869) * Fix homograph dict * Add JSON in dict * Adjust hot dict to hot reload * Add English name dict * Adjust get name dict logic * Make API Great Again (#894) * Add zh/jp/en mix * Optimize code readability and formatted output. * Try OGG streaming * Add stream mode arg * Add media type arg * Add cut punc arg * Eliminate punc risk * Update README (#895) * Update README * Update README * update README * update README * fix typo s/Licence /License (#904) * fix reformat cmd (#917) Co-authored-by: starylan <starylan@outlook.com> * Update README.md * Normalize chinese arithmetic operations (#947) * 改变训练和推理时的mask策略，以修复当batch_size>1时，产生的复读现象 * 同步main分支代码，增加“保持随机”选项 * 在colab中运行colab_webui.ipynb发生的uvr5模型缺失问题 (#968) 在colab中使用git下载uvr5模型时报错： fatal: destination path 'uvr5_weights' already exists and is not an empty directory. 通过在下载前将原本从本仓库下载的uvr5_weights文件夹删除可以解决问题。 * [ASR] 修复FasterWhisper遍历输入路径失败 (#956) * remove glob * rename * reset mirror pos * 回退mask策略； 回退pad策略； 在T2SBlock中添加padding_mask，以减少pad的影响； 开放repetition_penalty参数，让用户自行调整重复惩罚的强度； 增加parallel_infer参数，用于开启或关闭并行推理，关闭时与0307版本保持一致； 在webui中增加“保持随机”选项； 同步main分支代码。 * 删除无用注释 --------- Co-authored-by: Lion <drain.daters.0p@icloud.com> Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com> Co-authored-by: KamioRinn <snowsdream@live.com> Co-authored-by: Pengoose <pengoose_dev@naver.com> Co-authored-by: Yuan-Man <68322456+Yuan-ManX@users.noreply.github.com> Co-authored-by: XXXXRT666 <157766680+XXXXRT666@users.noreply.github.com> Co-authored-by: KamioRinn <63162909+KamioRinn@users.noreply.github.com> Co-authored-by: Lion-Wu <130235128+Lion-Wu@users.noreply.github.com> Co-authored-by: digger yu <digger-yu@outlook.com> Co-authored-by: SapphireLab <36986837+SapphireLab@users.noreply.github.com> Co-authored-by: starylan <starylan@outlook.com> Co-authored-by: shadow01a <141255649+shadow01a@users.noreply.github.com>
78 lines
3.0 KiB
Python
78 lines
3.0 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 only_asr(input_file):
|
|
try:
|
|
text = model.generate(input=input_file)[0]["text"]
|
|
except:
|
|
text = ''
|
|
print(traceback.format_exc())
|
|
return text
|
|
|
|
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 file_name in tqdm(input_file_names):
|
|
try:
|
|
file_path = os.path.join(input_folder, file_name)
|
|
text = model.generate(input=file_path)[0]["text"]
|
|
output.append(f"{file_path}|{output_file_name}|{language.upper()}|{text}")
|
|
except:
|
|
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.")
|
|
parser.add_argument("-p", "--precision", type=str, default='float16', choices=['float16','float32'],
|
|
help="fp16 or fp32")#还没接入
|
|
|
|
cmd = parser.parse_args()
|
|
execute_asr(
|
|
input_folder = cmd.input_folder,
|
|
output_folder = cmd.output_folder,
|
|
model_size = cmd.model_size,
|
|
language = cmd.language,
|
|
)
|