AIBase
Home
AI NEWS
AI Tools
GEO & AEO
MCP
AI Models
EN

AI News

View More

Comparable to GPT-4o! Fudan Introduces SpeechGPT2, a Voice Model that Can Understand Your Emotions

Fudan University has introduced SpeechGPT, a large language model designed to understand and generate both speech and text. By discretizing speech signals, it enables compatibility with text modalities, allowing for emotional perception and multi-style speech generation based on context and instructions. The training strategy includes modal adaptation pre-training, cross-modal instruction fine-tuning, and modal chain instruction fine-tuning to en....

25.9k 1 days ago
Comparable to GPT-4o! Fudan Introduces SpeechGPT2, a Voice Model that Can Understand Your Emotions

AI Products

View More
SpeechGPT 2.0-preview

SpeechGPT 2.0-preview

The first human-level real-time interactive system focused on contextual intelligence, supporting multi-emotional and multi-style voice interactions.

Speech to text
11.2k
SpeechGPT2

SpeechGPT2

An end-to-end human-like speech dialogue model.

AI voice assistant
16.4k
SpeechGPT

SpeechGPT

Multimodal Language Model

AI voice synthesis
16.9k

Models

View More

SpeechGPT 7B Cm

fnlp

S

SpeechGPT is a large language model with intrinsic cross-modal dialogue capabilities, capable of perceiving and generating multimodal content, supporting interaction via speech and text.

MultimodalTransformersTransformers
fnlp
47
7

SpeechGPT 7B Ma

fnlp

S

SpeechGPT is a large language model with intrinsic cross-modal dialogue capabilities, capable of perceiving and generating multimodal content based on human instructions.

MultimodalTransformersTransformers
fnlp
37
5
AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAI MarketingLLM LeaderboardAI Ranking
© 2026AIBase
Business CooperationSite Map