bacow/GPT-SoVITS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

Browse Source 
* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab
This commit is contained in:
XXXXRT666
2025-04-07 09:42:47 +01:00
committed by GitHub
parent 9da7e17efe
commit 53cac93589
132 changed files with 8185 additions and 6648 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
tools/asr/config.py
View File

@@ -1,33 +1,36 @@
import os
def check_fw_local_models():
'''
"""
启动时检查本地是否有 Faster Whisper 模型.
'''
"""
model_size_list = [
"tiny", "tiny.en",
"base", "base.en",
"small", "small.en",
"medium", "medium.en",
"large", "large-v1",
"large-v2", "large-v3"]
"tiny",
"tiny.en",
"base",
"base.en",
"small",
"small.en",
"medium",
"medium.en",
"large",
"large-v1",
"large-v2",
"large-v3",
]
for i, size in enumerate(model_size_list):
if os.path.exists(f'tools/asr/models/faster-whisper-{size}'):
model_size_list[i] = size + '-local'
if os.path.exists(f"tools/asr/models/faster-whisper-{size}"):
model_size_list[i] = size + "-local"
return model_size_list
asr_dict = {
"达摩 ASR (中文)": {
'lang': ['zh','yue'],
'size': ['large'],
'path': 'funasr_asr.py',
'precision': ['float32']
},
"达摩 ASR (中文)": {"lang": ["zh", "yue"], "size": ["large"], "path": "funasr_asr.py", "precision": ["float32"]},
"Faster Whisper (多语种)": {
'lang': ['auto', 'zh', 'en', 'ja', 'ko', 'yue'],
'size': check_fw_local_models(),
'path': 'fasterwhisper_asr.py',
'precision': ['float32', 'float16', 'int8']
"lang": ["auto", "zh", "en", "ja", "ko", "yue"],
"size": check_fw_local_models(),
"path": "fasterwhisper_asr.py",
"precision": ["float32", "float16", "int8"],
},
}

94
tools/asr/fasterwhisper_asr.py
View File

@@ -2,7 +2,7 @@ import argparse
import os
import traceback
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
import torch
@@ -11,6 +11,7 @@ from tqdm import tqdm
from tools.asr.config import check_fw_local_models
# fmt: off
language_code_list = [
"af", "am", "ar", "as", "az",
"ba", "be", "bg", "bn", "bo",
@@ -32,82 +33,97 @@ language_code_list = [
"te", "tg", "th", "tk", "tl",
"tr", "tt", "uk", "ur", "uz",
"vi", "yi", "yo", "zh", "yue",
"auto"]
"auto"]
# fmt: on
def execute_asr(input_folder, output_folder, model_size, language, precision):
if '-local' in model_size:
if "-local" in model_size:
model_size = model_size[:-6]
model_path = f'tools/asr/models/faster-whisper-{model_size}'
model_path = f"tools/asr/models/faster-whisper-{model_size}"
else:
model_path = model_size
if language == 'auto':
language = None #不设置语种由模型自动输出概率最高的语种
print("loading faster whisper model:",model_size,model_path)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
if language == "auto":
language = None # 不设置语种由模型自动输出概率最高的语种
print("loading faster whisper model:", model_size, model_path)
device = "cuda" if torch.cuda.is_available() else "cpu"
try:
model = WhisperModel(model_path, device=device, compute_type=precision)
except:
return print(traceback.format_exc())
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)
segments, info = model.transcribe(
audio = file_path,
beam_size = 5,
vad_filter = True,
vad_parameters = dict(min_silence_duration_ms=700),
language = language)
text = ''
audio=file_path,
beam_size=5,
vad_filter=True,
vad_parameters=dict(min_silence_duration_ms=700),
language=language,
)
text = ""
if info.language == "zh":
print("检测为中文文本, 转 FunASR 处理")
if("only_asr" not in globals()):
from tools.asr.funasr_asr import only_asr #如果用英文就不需要导入下载模型
if "only_asr" not in globals():
from tools.asr.funasr_asr import only_asr # 如果用英文就不需要导入下载模型
text = only_asr(file_path, language=info.language.lower())
if text == '':
if text == "":
for segment in segments:
text += segment.text
output.append(f"{file_path}|{output_file_name}|{info.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')
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__':
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-v3',
choices=check_fw_local_models(),
help="Model Size of Faster Whisper")
parser.add_argument("-l", "--language", type=str, default='ja',
choices=language_code_list,
help="Language of the audio files.")
parser.add_argument("-p", "--precision", type=str, default='float16', choices=['float16','float32','int8'],
help="fp16, int8 or fp32")
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-v3",
choices=check_fw_local_models(),
help="Model Size of Faster Whisper",
)
parser.add_argument(
"-l", "--language", type=str, default="ja", choices=language_code_list, help="Language of the audio files."
)
parser.add_argument(
"-p",
"--precision",
type=str,
default="float16",
choices=["float16", "float32", "int8"],
help="fp16, int8 or fp32",
)
cmd = parser.parse_args()
output_file_path = execute_asr(
input_folder = cmd.input_folder,
output_folder = cmd.output_folder,
model_size = cmd.model_size,
language = cmd.language,
precision = cmd.precision,
input_folder=cmd.input_folder,
output_folder=cmd.output_folder,
model_size=cmd.model_size,
language=cmd.language,
precision=cmd.precision,
)

79
tools/asr/funasr_asr.py
View File

@@ -9,31 +9,41 @@ import traceback
from funasr import AutoModel
from tqdm import tqdm
funasr_models = {} # 存储模型避免重复加载
funasr_models = {} # 存储模型避免重复加载
def only_asr(input_file, language):
try:
model = create_model(language)
text = model.generate(input=input_file)[0]["text"]
except:
text = ''
text = ""
print(traceback.format_exc())
return text
def create_model(language="zh"):
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_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 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"
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"
elif language == "yue":
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"
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 = None
vad_model_revision = punc_model_revision = None
@@ -45,25 +55,26 @@ def create_model(language="zh"):
return funasr_models[language]
else:
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,
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,
)
print(f"FunASR 模型加载完成: {language.upper()}")
funasr_models[language] = model
return model
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)
model = create_model(language)
for file_name in tqdm(input_file_names):
@@ -77,29 +88,31 @@ def execute_asr(input_folder, output_folder, model_size, language):
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')
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__':
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','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
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()
execute_asr(
input_folder = cmd.input_folder,
output_folder = cmd.output_folder,
model_size = cmd.model_size,
language = cmd.language,
input_folder=cmd.input_folder,
output_folder=cmd.output_folder,
model_size=cmd.model_size,
language=cmd.language,
)