def train_and_dump(dirs, start, end, output_model, features_save):
m = ModelInterface()
#print("len(dirs[start:end]):", len(dirs[start:end]))
for d in dirs[start:end]:
label = os.path.basename(d.rstrip('/'))
wavs = glob.glob(d + '/*.wav')
if len(wavs) == 0:
print("No wav file found in %s" % (d))
continue
for wav in wavs:
try:
fs, signal = read_wav(wav)
m.enroll(label, fs, signal)
#print("wav %s has been enrolled" % (wav))
except Exception as e:
print(wav + " error %s" % (e))
print("The group wav files has been enrolled")
# 如果指定了mfcc特征文件保存路径，则保存mfcc特征文件
if features_save:
m.mfcc_dump(features_save)
print(
"The features of this group wav files has been pickle.dumped to %s"
% features_save)
m.train()
m.dump(output_model)
print("%s has been pickle.dumped\t" % output_model)
def task_enroll(input_dirs,
output_model,
features_save=None,
group_person_num=None):
m = ModelInterface()
# 把输入的多个目录字符串分离为目录列表
input_dirs = [os.path.expanduser(k) for k in input_dirs.strip().split()]
# 把各个目录下的子目录列表解压出来组合成一个迭代器
dirs = itertools.chain(*(glob.glob(d) for d in input_dirs))
# 生成包括所有子目录的列表
dirs = [d for d in dirs if os.path.isdir(d)]
for d in dirs:
label = os.path.basename(d.rstrip('/'))
wavs = glob.glob(d + '/*.wav')
if len(wavs) == 0:
print("No wav file found in %s" % (d))
continue
for wav in wavs:
try:
fs, signal = read_wav(wav)
m.enroll(label, fs, signal)
#print("wav %s has been enrolled" % (wav))
except Exception as e:
print(wav + " error %s" % (e))
print("The wav files has been enrolled")
# 如果指定了mfcc特征文件保存路径，则保存mfcc特征文件
if features_save:
m.mfcc_dump(features_save)
print(
"The features of this group wav files has been pickle.dumped to %s"
% features_save)
m.train()
m.dump(output_model)
print("%s has been pickle.dumped\t" % output_model)
