AED | Automatic Emotion Detection | 自动情感检测 |
AI | Artificial Intelligence | 人工智能 |
ASR | Automatic Speech Recognition | 自动语音识别 |
CE | Cross Entropy | 交叉熵 |
ERP | erotic role playing | 情色角色扮演 |
FLCE | Fused Linear Cross Entropy | 融合线性交叉熵 |
FSDP | Fully Sharded Data Parallel | 完全分片数据并行 |
GeGLU | Gated Linear Unit | 门控线性单元 |
GELAN | Generalized Efficient Layer Aggregation Network | 通用高效层聚合网络 |
GME | Generalized Multimodal Encoder | 通用多模态编码器 |
GPT | Generative Pre-trained Transformer | 生成型预训练变换模型 |
GTE | Generalized Text Encoder | 通用文本编码器 |
ITN | Inverse Text Normalization | 逆文本规范化 |
LayerNorm | Layer Normalization | 层归一化 |
LID | Language Identification | 语言识别 |
LLaMa | Large Language Model for Machine Translation | 机器翻译的大语言模型 |
LLM | Large Language Model | 大语言模型 |
LoRA | Language of Rules and Actions | 语言规则与行动语言 |
PGI | Programmable Gradient Information | 可编程梯度信息 |
QLoRA | Quantized Low-Rank Adaptation | 量化低秩适配 |
RLHF | Reinforcement Learning from Human Feedback | 人类反馈强化学习 |
RM | Reward / preference modeling | 奖励/偏好建模 |
RMSNorm | Root Mean Square Normalization | 均方根归一化 |
RoPE | Rotary Position Embedding | 旋转位置嵌入 |
RTF | Real-Time Factor | 实时因子 |
SDXL | Stable Diffusion XL | 稳定扩散 XL |
SER | Speech Emotion Recognition | 语音情感识别 |
SFT | Supervised Fine-tuning | 监督微调 |
SOTA | State of the Art | 最新技术 |
STT | Speech to Text | 语音转文本 |
SwiGLU | Swish-Gated Linear Unit | Swish 门控线性单元 |
TTS | Text to Speech | 文本转语音 |
VAD | Voice Activity Detection | 语音活动检测 |
WFST | Weighted Finite-State Transducer | 加权有限状态转换器 |
YOLO | You Only Look Once | |