Real-time text-to-speech with Qwen3-TTS

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Finetune a pre-trained GPT-2 model to generate personalized product recommendations for users, based on product reviews and metadata

BirdiDQ leverages the power of the Python Great Expectations open-source library and combines it with the simplicity of natural language queries to effortlessly identify and report data quality iss…

We provide step-by-step guides, tutorials, and code snippets, allowing others to replicate our efforts with the Fula language or adapt our work

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Fula speech corpora for speech processing tasks

A multi-dialectal speech recognition models for Fula varieties

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

A Python package for PII data anonymization in French

The aim of this study is to point out a customer-oriented behavior by analyzing emails sent by companies to users. An intuitive idea to underline such a behavior. An intuitive idea to underline suc…