handler.py

from typing import Dict, List, Any
from transformers import AutoProcessor, MusicgenForConditionalGeneration
import torch

processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")

inputs = processor(
    text=["80s pop track with bassy drums and synth", "90s rock song with loud guitars and heavy drums"],
    padding=True,
    return_tensors="pt",
)

audio_values = model.generate(**inputs, max_new_tokens=256)

class EndpointHandler:
    def __init__(self, path=""):
        # load model and processor from path
        self.processor = AutoProcessor.from_pretrained(path)
        self.model = MusicgenForConditionalGeneration.from_pretrained(path)
        # self.model =  AutoModelForSeq2SeqLM.from_pretrained(path, device_map="auto", load_in_8bit=True)
        # self.tokenizer = AutoTokenizer.from_pretrained(path)

    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
        """
        Args:
            data (:dict:):
                The payload with the text prompt and generation parameters.
        """
        # process input
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)

        # preprocess
        # input_ids = self.tokenizer(inputs, return_tensors="pt").input_ids
        inputs = processor(
            text=inputs,
            padding=True,
            return_tensors="pt",)

        # pass inputs with all kwargs in data
        if parameters is not None:
            outputs = self.model.generate(inputs, max_new_tokens=256, **parameters)
        else:
            outputs = self.model.generate(inputs, max_new_tokens=256)

        # postprocess the prediction
        prediction = outputs[0].numpy()

        return [{"generated_audio": prediction}]