from peft import PeftModel
from transformers import WhisperForConditionalGeneration, WhisperProcessor
import torch

base = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
model = PeftModel.from_pretrained(base, "LakoreAI/whisper-small-vi-lora")
processor = WhisperProcessor.from_pretrained("LakoreAI/whisper-small-vi-lora")

# Optional: merge LoRA for faster inference
model = model.merge_and_unload()
model.eval()

# Inference
def transcribe(audio_array, sampling_rate=16000):
    inputs = processor(audio_array, sampling_rate=sampling_rate, return_tensors="pt")
    with torch.no_grad():
        ids = model.generate(
            inputs.input_features,
            language="vietnamese",
            task="transcribe",
            max_new_tokens=225,
        )
    return processor.tokenizer.decode(ids[0], skip_special_tokens=True)

Limitations

Optimized for Vietnamese only; other languages will degrade significantly
Common Voice data skews toward read speech; spontaneous/accented speech may perform worse
Short clips (<1s) or clipped audio may cause hallucinations