zhangyike
Follow
Stars
PyTorch Implementation of Stepwise Monotonic Multihead Attention similar to Enhancing Monotonicity for Robust Autoregressive Transformer TTS
PyTorch implementation of Tacotron and Tacotron2
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
Data and code for grapheme-to-phoneme transducers in lots of languages
A generative speech model for daily dialogue.
Datasets for Evaluation on Domain Knowledge Graph
An Instruction-tuned Large Language Model for E-commerce
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
This is now the official location of the Merlin project.
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding
Audio captioning - DCASE challenge 2023 task 6a
Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...
Modules to convert numbers to words. 42 --> forty-two
State of the Art Natural Language Processing
Command line utility for forced alignment using Kaldi
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…
👾 Fast and simple video download library and CLI tool written in Go
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
WavPack encode/decode library, command-line programs, and several plugins
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…