- Shanghai
-
00:08
- 8h ahead - https://zhikangniu.github.io/
Lists (19)
Sort Name ascending (A-Z)
Stars
这是一个从头训练大语言模型的项目,包括预训练、微调和直接偏好优化,模型拥有1B参数,支持中英文。
The official implementation of OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
TerDiT: Ternary Diffusion Models with Transformers
Scaling Diffusion Transformers with Mixture of Experts
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
Official repository of the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization".
Minimal implementation of scalable rectified flow transformers, based on SD3's approach
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
制作懂人情世故的大语言模型 | 涵盖提示词工程、RAG、Agent、LLM微调教程
LibriSpeech-Long is a benchmark dataset for long-form speech generation and processing. Released as part of "Long-Form Speech Generation with Spoken Language Models" (arXiv 2024).
SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.
A curated list of reinforcement learning with human feedback resources (continually updated)
InspireMusic: A Unified Framework for Music, Song, Audio Generation.
phoneme tokenizer and grapheme-to-phoneme model for 8k languages
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
A python package for deep multilingual punctuation prediction.
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Transcription, forced alignment, and audio indexing with OpenAI's Whisper
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
Pushing the Limits of Zero-shot End-to-End Speech Translation
[TASLP 2024] Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation
A curated list of resources for using LLMs to develop more competitive grant applications.
Train a 1B LLM with 1T tokens from scratch by personal