CDJG10/wav2vec2-mam-usac

Automatic Speech Recognition (ASR) for the Mam Language

This model is a fine-tuned version of Meta's Wav2Vec2 XLS-R (300M) architecture, specifically adapted for phonetic recognition and automatic transcription of the Mam language. The development of this system was carried out as a scientific research and engineering project at the Universidad de San Carlos de Guatemala (USAC), aimed at creating accessible language technology tools for low-resource languages.

License and Terms of Use

This repository is distributed under the international Creative Commons Attribution-NonCommercial 4.0 (CC BY-NC 4.0) license.

You are free to:

• Share: Copy and redistribute the material in any medium or format.
• Adapt: Remix, transform, and build upon the material for research purposes, educational software development, or cultural preservation.

Under the following terms:

• Attribution (BY): You must give appropriate credit to the original author, provide a link to the license, and indicate if changes were made to the model weights or structure.
• NonCommercial (NC): You may not use this model, its mathematical weights, or its derivatives for commercial purposes, profit, or direct/indirect monetization. Any integration into paid corporate systems, commercial APIs, or proprietary software tools requires express, written, and prior authorization from the research rights holder.