/wolof_speech_recognition

Primary LanguageJupyter NotebookOtherNOASSERTION

Wolof_speech_recognition

The goal of this project is to collect data in our local language and fine tunea phone classification model. For our case we will be using wolof. Wolof is alanguage of Senegal, the Gambia and Mauritania, and the native language ofthe Wolof people. The successful completion of this project would have been much more difficult, if it wasn't for the generous support, provided by Professor Laurent Besacier, Univ. Grenoble Alpes. Thanks also to the Lig-Aikuma project for providing the platform to record and create this dataset.

1. Recording audio in wolof language

2. Using Pretrained English model and fine tune

3. Evaluate performance of the model using Phone Error Rate(PER) and Caracter Error Rate(CER)

Here is the link to access to the records data from google drive https://drive.google.com/drive/folders/1gxHWLdx5cgcpPOdDzXJUuE29hmzZbROJ?usp=sharing