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. -->
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