wav2vec2-nepali

Model Card for wav2vec2-nepali

<!-- Provide a quick summary of what the model is/does. -->

wav2vec2-nepali is the fine-tuned model for Nepali language, developed by finetuning the Facebook's wav2vec2 speech recognition model

Model Details

This model is fine-tuned on Nepali language dataset, so it can be used for transcribing Nepali speech. This model can convert Nepali speech to text with a good accuracy of 91% in normal conditions.

• Developed by: Anish Shilpakar
• Language(s) (NLP): [Nepali]
• Finetuned from model [optional]: wav2vec2

Uses

• For Nepali speech to text transcription
• Can be used for Nepali voice typing
• Can be integrated with other systems like speech summarizer, translation systems.

Training Details

Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

OpenSLR

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Training Notebook

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

Character Error Rate Word Error Rate