from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

# Load model and processor
processor = WhisperProcessor.from_pretrained("Bijay13/whisper-small-ne-en-finetuned-v2")
model = WhisperForConditionalGeneration.from_pretrained("Bijay13/whisper-small-ne-en-finetuned-v2")

# Load audio
audio, sr = librosa.load("your_audio.wav", sr=16000)

# Transcribe
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features
predicted_ids = model.generate(input_features)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
print(transcription)

License

Base Model: openai/whisper-small
Language: Nepali-English (code-switched)
Task: transcribe
Fine-tuned on: Custom Nepali ASR dataset

This model is released under the Apache 2.0 license.