hubert hf

minigpt4/conversation/conversation.py

@@ -260,7 +260,8 @@ class Chat:
             samples, sr = extract_audio_from_video(video_path)
             # print("samples:", samples)
 
-            model_file = "checkpoints/transformer/chinese-hubert-large"
+            # model_file = "checkpoints/transformer/chinese-hubert-large"
+            model_file = "ZebangCheng/chinese-hubert-large"
             feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_file)
             input_values = feature_extractor(samples, sampling_rate=sr, return_tensors="pt").input_values
             # print("input_values:", input_values)

minigpt4/datasets/datasets/first_face.py

@@ -12,13 +12,11 @@ import torch.nn.functional as F
 
 import numpy as np
 from PIL import Image
-import skimage.io as io
 import matplotlib.pyplot as plt
 from matplotlib.collections import PatchCollection
 from matplotlib.patches import Polygon, Rectangle
 import torch
 from torch.utils.data import Dataset
-import webdataset as wds
 import cv2
 
 from minigpt4.datasets.datasets.base_dataset import BaseDataset