Pinned Repositories
AlphaGo-Zero-Othello
利用AlphaGo Zero实现的黑白棋AI。
awesome-data
Awesome datasets curated. By topic and for core data https://datahub.io/docs/core-data
blogs-collection
chatgpt-clone
Build Yo'own ChatGPT with OpenAI API & Gradio
FastDocument
HarvestText
文本挖掘和预处理工具（文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等），无监督或弱监督方法
kanchil
Kanchil（鼷鹿）是世界上最小的偶蹄目动物，这个开源项目意在探索小模型（6B以下）是否也能具备和人类偏好对齐的能力。
marseille
Mining Argument Structures with Expressive Inference (Linear and LSTM Engines)
svoice
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
vxfla's Repositories
vxfla/kanchil
Kanchil（鼷鹿）是世界上最小的偶蹄目动物，这个开源项目意在探索小模型（6B以下）是否也能具备和人类偏好对齐的能力。
vxfla/AlphaGo-Zero-Othello
利用AlphaGo Zero实现的黑白棋AI。
vxfla/awesome-data
Awesome datasets curated. By topic and for core data https://datahub.io/docs/core-data
vxfla/blogs-collection
vxfla/chatgpt-clone
Build Yo'own ChatGPT with OpenAI API & Gradio
vxfla/FastDocument
vxfla/HarvestText
文本挖掘和预处理工具（文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等），无监督或弱监督方法
vxfla/marseille
Mining Argument Structures with Expressive Inference (Linear and LSTM Engines)
vxfla/svoice
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
vxfla/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
vxfla/UltraChat
Large-scale, Informative, and Diverse Multi-round Dialogue Data
vxfla/vxfla.github.io
vxfla/X2Paddle
Deep learning model converter for PaddlePaddle. (『飞桨』深度学习模型转换工具)