Stars
This repository uses a seq2seq model to translate custom input data formats into fixed, normalized formats like UTC or others. If you are working on another NLP task that requires a custom translat…
A library to make augmented audio (8/16 kHz, mono, WAV PCM) with noises corpora.
Linguini is a benchmark to measure a language model’s linguistic reasoning skills without relying on pre-existing language-specific knowledge, based on the International Linguistic Olympiad problems.
The python library and service for automatic speech recognition and transcribing in Russian and English
Agentic RAG implementation via a Telegram bot.
Simple neuroevolution AI example using pygame & NEAT python.
T5-based (russian) text normalization
An open-source framework for training large multimodal models.
Парсер диалогов из чатов в telegram, сохранение в instruct формате для llama
Generate Russian text using GPT model given LaBSE text embedding vector
Русскоязычный генеративный чатбот с профилем и фактами
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
💩🚀 Windows 95 in Electron. Runs on macOS, Linux, and Windows.
telegram chat with bots on the language model tinkoff-ai/ruDialoGPT-medium