Introduction: ESG (Environmental, Social, and Governance) criteria are a framework used to assess an organization’s performance on various sustainability and ethical issues in the respective areas of environmental, social, and governance. Some important topics include carbon footprint of organization’s bussiness, employee ethical treatment, maintaining fair relationship with stakeholders and partners.

Introduction The landscape of generative models is rapidly changing. The recent releases in LLM architecture models include the GPT-4 model from OpenAI and the open-source Llama2 from MetaAI. For AI practitioners, one of the key factors beyond all criteria when choosing the right solution for their business is the cost of…

Introduction After introducing the speaker diarization problem and presenting the 2 main state-of-the-art frameworks pyannote.audio and NeMo, this third article on speaker diarization aims at presenting more in detail how a speaker diarization pipeline can be tuned to get the best results for specific purposes. We emphasize on understanding how the…

Notre implémentation NeMo + Whisper permet actuellement de générer des scripts de 1h de contenu audio en seulement 4 minutes pour des conversations jusqu’à 8 locuteurs. Aujourd’hui, de nombreux contenus à caractère éducatif et culturel sont enregistrés sous la forme de podcasts audio avec plusieurs intervenants. Ce format vivant et…

Introduction In the previous article of this series, the concept of speaker diarization or finding “who spoke when?” has been introduced along with the typical architecture of modern speaker diarization pipelines. …

Introduction Speaker diarization is the process of automatically identifying and segmenting an audio recording into distinct speech segments, where each segment corresponds to a particular speaker. In simpler words, the goal is to answer the question: who spoke when? It involves analyzing the audio signal to detect changes in speaker identity…

1. Introduction In many of our projects, we deal with the problem of understanding cause-consequence, time-object or place-object relationships. Imagine that we try to understand this customer request: Example 1: “I have received the invoice for January & March 2022 but the February 2022 invoice is missing. …

Cet article a pour but d’expliquer quelques-uns des algorithmes de recherche de similarité implémentés dans faiss, une bibliothèque développée par facebook, que j’ai découverte à l’occasion d’un projet de NLP. …

Clustering des thématiques de spams Introduction Données Les données traitées sont des mails reçus par des particuliers et signalés à signal-spam. Ce genre de mails frauduleux peut venir sous plusieurs formats : texte texte + pièce jointe photo (texte contenu dans une photo collée dans le mail) une combinaison de tous ces…