|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- mozilla-foundation/common_voice_11_0 |
|
language: |
|
- ur |
|
base_model: |
|
- openai/whisper-medium |
|
pipeline_tag: automatic-speech-recognition |
|
library_name: transformers |
|
--- |
|
|
|
|
|
# Whisper Medium Urdu Model |
|
|
|
This model is a fine-tuned version of OpenAI's Whisper model for automatic speech recognition (ASR) in **Urdu**. It is trained on various audio datasets and is designed to convert spoken Urdu language into text. |
|
|
|
## Model Description |
|
|
|
The **Whisper** model is a general-purpose ASR system trained on a large multilingual dataset, capable of transcribing speech to text in many languages, including Urdu. This specific model has been fine-tuned on Urdu audio datasets for better accuracy with Urdu speech inputs. |
|
|
|
### Key Features: |
|
- **Language:** Urdu |
|
- **Model Type:** Whisper medium model |
|
- **Task:** Automatic Speech Recognition (ASR) |
|
- **Training Data:** The model was trained on a diverse set of Urdu speech data. |
|
|
|
## Intended Use |
|
|
|
This model is intended for automatic transcription of Urdu speech to text. It can be used for applications such as: |
|
- Speech-to-text transcription in Urdu |
|
- Transcription for Urdu audio or video content |
|
- Accessibility features for Urdu-speaking users |
|
|
|
## How to Use |
|
|
|
You can easily use the model with the Hugging Face `transformers` library: |
|
|
|
```python |
|
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq |
|
|
|
# Load the model and processor |
|
processor = AutoProcessor.from_pretrained("Abdul145/whisper-medium-urdu-custom") |
|
model = AutoModelForSpeechSeq2Seq.from_pretrained("Abdul145/whisper-medium-urdu-custom") |
|
|
