Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Urdu
whisper
Speech
ASR
Whisper-fine-tuning
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("shaeel12/whisper-tiny-urdu")
model = AutoModelForSpeechSeq2Seq.from_pretrained("shaeel12/whisper-tiny-urdu", device_map="auto")Quick Links
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.
- Downloads last month
- 5
Model tree for shaeel12/whisper-tiny-urdu
Base model
openai/whisper-tiny
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="shaeel12/whisper-tiny-urdu", device_map="auto")