---
language:
- ur
metrics:
- wer
base_model:
- openai/whisper-tiny
pipeline_tag: automatic-speech-recognition
library_name: transformers
tags:
- Speech
- ASR
- Whisper-fine-tuning
datasets:
- ai4bharat/Kathbath
- google/fleurs
---
This model was fine-tuned on a combination of the following speech corpuses:
* **ai4bharat/Kathbath** (via Hugging Face)
* **google/fleurs** (via Hugging Face)
* **Mozilla Common Voice (Urdu Subset):** Sourced directly from the official [Mozilla Data Collective](https://datacollective.mozillafoundation.org).