metadata
language:
- ta
metrics:
- wer
pipeline_tag: automatic-speech-recognition
library_name: adapter-transformers
Model Card for Model ID
This model is a fine-tuned version of XLS-R on Tamil speech data from Tamil Vulnerable Speech Recognition.
Model Details
Model Description
- Model type: [Transfoemr based model]
- Language(s) : [Tamil]
- Finetuned from model [optional]: [XLS-R]
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Thw model is used to perform speech-to-text in Tamil.
Direct Use
[More Information Needed]
Downstream Use [optional]
Tammil Speech Recogniton
Training Details
Training Data
Tamil vulnerable speech dataset.
Preprocessing [optional]
All the .wav files are resampled to 16000 Hz and Log-Mel Spectrogram is extracted