Collection of Portuguese datasets for training and evaluating language models encompassing different tasks.
Afonso Marques
marquesafonso
AI & ML interests
None yet
Recent Activity
upvoted an article about 19 hours ago
Optimum Intel 2.0: An OpenVINO-First Toolkit for Running Open Models on Intel upvoted an article 4 days ago
Designing the hf CLI as an agent-optimized way to work with the Hub upvoted an article 10 days ago
How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or AccentOrganizations
None yet
Collection of Portuguese datasets for training and evaluating language models encompassing different tasks.
Content creation tool suite: multilingual ASR, video/audio transcription and direct captioning (faster-whisper), audio separation, waveform animation.
Model card adaptations of Bertimbau (published by neuralmind-ai) for compatibility with the transformers library for tasks of portuguese NER.
OpenVINO IR format and nncf format quantized models of Nuexctract by NuMind. See their work at: https://huggingface.co/numind