| from typing import Dict, List, Any | |
| from transformers import pipeline, WhisperProcessor, WhisperForConditionalGeneration | |
| import torch | |
| class EndpointHandler(): | |
| def __init__(self, path=""): | |
| device = 0 if torch.cuda.is_available() else "cpu" | |
| self.pipe = pipeline( | |
| task="automatic-speech-recognition", | |
| model=path, | |
| chunk_length_s=30, | |
| device=device, | |
| ) | |
| def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]: | |
| """ | |
| data args: | |
| inputs (:obj: `str` | `PIL.Image` | `np.array`) | |
| kwargs | |
| Return: | |
| A :obj:`list` | `dict`: will be serialized and returned | |
| """ | |
| inputs = data.pop("inputs",data) | |
| print("inputs", inputs) | |
| prediction = self.pipe(inputs, return_timestamps=True) | |
| return prediction |