MERaLiON-2-3B-DPO-CodeSwitch

from meralion2_model.modeling_meralion2 import MERaLiON2ForConditionalGeneration
from meralion2_model.processing_meralion2 import MERaLiON2Processor
import torch
import librosa

# Load model
model = MERaLiON2ForConditionalGeneration.from_pretrained(
    "myaccountfor/MERaLiON-2-3B-DPO-CodeSwitch",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
processor = MERaLiON2Processor.from_pretrained(
    "myaccountfor/MERaLiON-2-3B-DPO-CodeSwitch",
    trust_remote_code=True
)

model.eval()

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

# Build prompt
prompt = "Please transcribe this speech."
input_text = f"Instruction: {prompt} \nFollow the text instruction based on the following audio: <SpeechHere>"

# Apply chat template
conversation = [{"role": "user", "content": input_text}]
chat_prompt = "<bos><start_of_turn>user\n" + input_text + "<end_of_turn>\n<start_of_turn>model\n"

# Process inputs
inputs = processor(text=[chat_prompt], audios=[audio])
inputs = {k: v.to(model.device) for k, v in inputs.items()}

# Generate
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        do_sample=False,
        use_cache=True,
    )
    generated_ids = outputs[:, inputs['input_ids'].size(1):]
    transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(transcription)