|
from typing import Dict, List, Any |
|
from transformers import AutoProcessor, MusicgenForConditionalGeneration |
|
import torch |
|
|
|
class EndpointHandler: |
|
def __init__(self, path=""): |
|
|
|
self.processor = AutoProcessor.from_pretrained(path) |
|
self.model = MusicgenForConditionalGeneration.from_pretrained(path, torch_dtype=torch.float16).to("cuda") |
|
|
|
def __call__(self, data: Dict[str, Any]) -> Dict[str, str]: |
|
""" |
|
Args: |
|
data (:dict:): |
|
The payload with the text prompt and generation parameters. |
|
""" |
|
|
|
inputs = data.pop("inputs", data) |
|
parameters = data.pop("parameters", None) |
|
|
|
|
|
inputs = self.processor( |
|
text=[inputs], |
|
padding=True, |
|
return_tensors="pt",).to("cuda") |
|
|
|
|
|
with torch.autocast("cuda"): |
|
outputs = self.model.generate(**inputs, do_sample=False, max_new_tokens=400) |
|
|
|
|
|
prediction = outputs[0].cpu().numpy().tolist() |
|
|
|
return [{"generated_audio": prediction}] |