介绍
快速入门
语音转文本
文本到语音
发布的模型
演示
API 参考
EmbeddingMeta
SpecClustUnorm
SpecCluster
distribute_overlap()
do_AHC()
do_spec_clustering()
get_oracle_num_spkrs()
is_overlapped()
merge_ssegs_same_speaker()
read_rttm()
spectral_clustering()
spectral_embedding()
write_ders_file()
write_rttm()
Ndx
PLDA
分数
fa_model_loop()
ismember()
AddBabble
AddNoise
AddReverb
DropChunk
DropFreq
EnvCorrupt
重采样
SpeedPerturb
时间域规范增强
构建增强管道()
waveform_augment()
批量特征归一化()
batch_pad_right()
feature_normalize()
pad_right_2d()
pad_right_to()
waveform_collate_fn()
CSVDataset
meta_info
JSON数据集
InputNormalization
blackman_window()
compute_amplitude()
convolve1d()
dB_to_amplitude()
normalize()
notch_filter()
重新缩放()
reverberate()
AttentiveStatisticsPooling
BatchNorm1d
Conv1d
EcapaTdnn
Res2NetBlock
SEBlock
SERes2NetBlock
TDNNBlock
length_to_mask()
LSTMSpeakerEncoder
梯度反转函数
GradientReversalLayer
AdditiveAngularMargin
AngularMargin
FocalLoss
GE2ELoss
LogSoftmaxWrapper
NCELoss
SpeakerIdetification
CyclicLRScheduler
seed_everything()
Timer
seconds_to_hms()
Q_from_tokens()
get_chunks()