Phi-4-multimodal-DPO

from transformers import AutoModelForCausalLM, AutoProcessor
import soundfile as sf

# Load model
model = AutoModelForCausalLM.from_pretrained(
    "myaccountfor/Phi-4-multimodal-DPO",
    trust_remote_code=True,
    torch_dtype="auto",
    device_map="auto"
)
processor = AutoProcessor.from_pretrained(
    "myaccountfor/Phi-4-multimodal-DPO",
    trust_remote_code=True
)

# Load audio
audio, sr = sf.read("your_audio.wav")

# Build prompt
prompt = "<|user|><|audio_1|>Please transcribe this speech.<|end|><|assistant|>"

# Process and generate
inputs = processor(text=prompt, audios=[(audio, sr)], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
transcription = processor.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0]
print(transcription)