from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

# Load model and processor
processor = WhisperProcessor.from_pretrained("vanshnawander/whisper-small-hindi-asr")
model = WhisperForConditionalGeneration.from_pretrained("vanshnawander/whisper-small-hindi-asr")

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

# Transcribe
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features
generated_ids = model.generate(input_features, language="hi", task="transcribe")
transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(transcription)

Using Pipeline

python

from transformers import pipeline

pipe = pipeline(
    "automatic-speech-recognition",
    model="vanshnawander/whisper-small-hindi-asr",
    chunk_length_s=30,
)

result = pipe("audio.wav", generate_kwargs={"language": "hi", "task": "transcribe"})
print(result["text"])

Limitations

Optimized for Hindi speech; may not perform well on other languages
Best performance on clear audio with minimal background noise
May struggle with very fast speech or heavy code-mixing