rustambekurokov/navo-uz

from transformers import WhisperForConditionalGeneration, WhisperProcessor
import librosa

model_id = "whiteh4t/navo-uz"

processor = WhisperProcessor.from_pretrained(model_id)
model = WhisperForConditionalGeneration.from_pretrained(model_id)

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

inputs = processor(audio, sampling_rate=16000, return_tensors="pt")
predicted_ids = model.generate(
    inputs.input_features,
    language="uz",
    task="transcribe",
    max_new_tokens=225,
)

text = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
print(text)